Tracked Repositories
2045
Cognaptus DataHub Monitor
GitHub Resources from arXiv Digests
A monitored reference page for GitHub repositories surfaced from arXiv-paper digests, rendered from a machine-generated local data file.
Unique Papers
1563
Core Fields
paper title, ref_id, GitHub URL
Refresh Mode
local data file written by backend tasks
How To Use This Page
Use it as a lightweight index of implementation assets surfaced from research digests. The page stays defensive: required fields remain visible even when optional metadata is missing.
This page is designed as a refreshable reference surface rather than a hand-maintained article.
The goal is simple: when paper-digest workflows identify linked GitHub repositories, keep them visible in one place with enough context to scan quickly and revisit later.
Repository Index
Search by paper title, arXiv reference, GitHub repository, author, or tags when those fields are available.
Repository containing code, configurations, prompts, and data-processing utilities for according-to prompting and QUIP-Score experiments.
orionw/according-to
implementation
Official repository for the paper containing the in-the-wild prompt corpus, forbidden-question set, ChatGLM evaluator, and semantic-visualization code.
verazuo/jailbreak_llms
dataset
Repository containing code and results for the LLM-based zero-shot tree induction and embedding experiments, with feature-description files referenced for private-dataset feature names.
ml-lab-htw/llm-trees
implementation
Repository containing code and data for replicating the paper's LIME and SP-LIME experiments.
marcotcr/lime-experiments
Repository linked by the paper as the code for PriorDynaFlow, the proposed a priori dynamic multi-agent workflow construction framework.
L1n111ya/PriorDynaFlow
framework
Repository for the KindsOfReasoning collection and raw outputs/evaluation results for OpenAI instruction-tuned models.
Kinds-of-Intelligence-CFI/KindsOfReasoning
dataset
Repository identified by the paper as containing code for the empirical experiments.
LoryPack/ReferenceInstancesPredictability
implementation
Repository containing the experimental software associated with the proposed causal evaluation framework for deferring systems.
andrepugni/PODS
implementation
Python, notebook, and spreadsheet materials for driver ranking, forced ARMA changes, and related paper experiments.
omhariyadav20/causal_drivers
dataset
EvolveGCN repository data folder referenced as the source for the SBM dynamic graph benchmark.
IBM/EvolveGCN
dataset
Repository containing datasets and code files supporting the paper's DeepSeek-versus-other-LLMs benchmark.
ZhengTracyKe/DeepSeek-and-other-LLMs
dataset
Repository containing accompanying code and resources for the book, including chapter folders and Python-oriented examples for XAI techniques.
Echoslayer/XAI_From_Classical_Models_to_LLMs
implementation
Aegis is an open-source defense system directly evaluated as one of the paper's jailbreak defenses.
automorphic-ai/aegis
The paper's LLM Jailbreak Attack-Defense Arena implementation, containing attack and defense modules, benchmark data, evaluation utilities, and support for the three tested models.
ltroin/llm_attack_defense_arena
benchmark
LLM Guard is an open-source LLM security toolkit directly evaluated in the paper's defense benchmark.
protectai/llm-guard
An implementation referenced for reducing GPU all-to-all communication bottlenecks in large-scale MoE execution.
deepseek-ai/DeepEP
system
A GitHub repository associated with the survey that organises resources and representative work on self-evolving AI agents.
EvoAgentX/Awesome-Self-Evolving-Agents
Repository implementing the LED baselines, evidence-selection scaffold, shorter-context experiments, heuristic evidence baselines, and evaluation workflow reported for QASPER.
allenai/qasper-led-baseline
Repository containing the EIIE portfolio-management code, configurations, figures, tables, and data used for the cryptocurrency replication and stock-market extension.
jackieli19/PGPortfolio
framework
PGPortfolio (Policy Gradient Portfolio), the authors' source-code repository implementing the paper's deep reinforcement-learning portfolio framework.
ZhengyaoJiang/PGPortfolio
AIDE-ML: AI-Driven Exploration in the Space of Code, used as the agentic AutoML baseline/interface for observing decisions and artifacts.
WecoAI/aideml
framework
Git repository providing open access to the research datasets supporting the study's findings and replication.
bigrasam/CRNData
dataset
Source code for a minimal MedLog prototype using an OpenAPI-described HTTP REST interface.
mims-harvard/medlog
system
Repository for the financial news dataset used with permission as part of the paper's Bloomberg dataset experiments.
philipperemy/financial-news-dataset
dataset
Open implementation code for the TGN-SEAL framework introduced and evaluated in the paper.
nssajadi/tgn-seal
framework
Public codebase containing the Agent-Driver pipeline, tool library, cognitive memory, reasoning engine, scripts for fine-tuning and inference, prepared data layout, and nuScenes evaluation workflow.
physical-superintelligence-lab/Agent-Driver
framework
The public Lean 4/Mathlib library containing the formalized QAOA and Ising-ring components, the lower-bound and attainability theorems, and the machine-checked proof of residualEnergy_isLeast.
urikol/QuantumOptimization
Repository released by the authors for the minimal agentic theorem prover and experiment reproduction.
Axiomatic-AI/ax-prover-base
framework
Official code repository for interaction-aware retargeting, retargeted trajectories, Isaac Lab task environments, PPO training, and evaluation scripts for the paper.
yunhaif/regrind
Repository for the CLINC150 intent-classification and out-of-scope evaluation data used in the experiments.
clinc/oos-eval
dataset
Repository for the StackOverflow short-text intent dataset evaluated by the paper.
jacoxu/StackOverflow
dataset
Repository containing the Banking77 fine-grained banking-intent dataset evaluated by the paper.
PolyAI-LDN/task-specific-datasets
dataset
Repository for a hybrid LSTM, multi-head attention, Gaussian fuzzy-rule, and ARIX local-model forecasting system, including folders for LSTM, Transformer, Neuro-fuzzy, data utilities, model code, and an experiment notebook.
mihaozbot/Fuzzy-transformer
system
R-based analysis and reporting pipeline orchestrated with DVC, with scripts, parameters, environment configuration, intermediate outputs, and instructions for reproducing the reported results.
tmr-crypto/wf_optim_crypto_analysis
implementation
Repository containing code used for the paper, including notebooks and utilities for the daily trading strategy, the CNN model with the new loss, data downloading/processing, baselines, and analysis.
Tony-Guo-1/daily_trading_strategy
system
Repository containing Python, R, and notebook implementations, data files, portfolio outputs, and figures associated with the dynamic stock-recommendation study.
AI4Finance-Foundation/Dynamic-Stock-Recommendation-Machine_Learning-Published-Paper-IEEE
implementation
Repository for Dedupe, the SVM-distance and hierarchical-clustering baseline evaluated against PDDM-AL.
dedupeio/dedupe
Repository associated with the proposed red-teaming framework, containing generated faithfulness/completeness datasets and prompt materials; the paper states that model configurations, evaluation scripts, standardized judge instructions, attacker prompts, and consensus aggregation code are made available there.
Raed-Mughaus/Red-Teaming-Datasets
A repository created to keep pace with the fast-moving literature on LLMs and LLM-based agents in science.
ur-whitelab/LLMs-in-science
Repository released by the author for resources associated with the LLM-agent survey.
xinzhel/LLM-Agent-Survey
TensorTrade is cited as an open-source package/platform relevant to implementing and adapting RL methods to finance.
tensortrade-org/tensortrade
framework
Official code repository for the paper's Agora implementation and heterogeneous 100-agent demonstration.
agora-protocol/paper-demo
The GitHub repository contains the self-improving coding-agent implementation introduced by the paper.
MaximeRobeyns/self_improving_coding_agent
framework
FakeNewsNet repository containing fake-news research data resources and crawler tooling for collecting news and related social-media data.
KaiDMML/FakeNewsNet
dataset
Repository containing the resulting mind map, collected notes for each reviewed grey resource, and an online repository of references for further exploration.
SAILResearch/replication-24-harsh-generative-ai-release-readiness-checklist
dataset
The Google Agent2Agent protocol repository, reviewed as a general-purpose inter-agent protocol and used in the paper's comparative use-case analysis.
google/A2A
Repository for the Web-Agent Protocol, reviewed as a domain-specific inter-agent or human-computer interaction protocol.
OTA-Tech-AI/web-agent-protocol
Repository for the agents.json specification, reviewed as a domain-specific context-oriented protocol for exposing website capabilities to agents.
wild-card-ai/agents-json
Companion repository maintained by the authors to track ongoing developments in AI agent protocols.
zoe-yyx/Awesome-AIAgent-Protocol
Author-maintained companion repository containing the survey's framework materials and a curated, stage-organized list of AI Scientist papers, systems, benchmarks, and applications.
Mr-Tieguigui/Survey-for-AI-Scientist
An Awesome Data Agents repository linked directly in the paper header, likely used to collect or organize data-agent resources associated with the survey.
HKUSTDial/awesome-data-agents
JoyAgent is discussed as a proto-L3 system that begins to address predefined-toolset limitations through tool evolution and multi-level thinking.
jd-opensource/joyagent-jdgenie
system
GitHub repository established by the authors as the project page associated with the survey on embodied learning for object-centric robotic manipulation.
RayYoh/OCRM_survey
Repository linked by the paper as the full list of surveyed papers and summary slides.
junhua/awesome-finance-ai-papers
Repository for AlphaFin, a benchmark/resource associated with financial question answering and stock prediction.
AlphaFin-proj/AlphaFin
dataset
Repository for R-Judge, a benchmark for safety judgment and risk identification.
Lordog/R-Judge
benchmark
Repository for FinanceBench, a financial question-answering benchmark.
patronus-ai/financebench
dataset
Repository for a Japanese financial language-model benchmark.
pfnet-research/japanese-lm-financial-benchmark
benchmark
Repository for BBT-Fin/CUGE-related Chinese financial language benchmark resources.
ssymmetry/BBT-FinCUGE-Application
benchmark
Repository for FinEval, a Chinese benchmark for financial domain knowledge.
SUFE-AIFLM-Lab/FinEval
benchmark
Repository for PIXIU/FinMA-related financial LLM resources, instruction data, and evaluation benchmarks.
The-FinAI/PIXIU
dataset
Repository for CFBenchmark, a Chinese financial benchmark covering multiple financial NLP tasks.
TongjiFinLab/CFBenchmark
benchmark
Repository for DocMath-Eval, used for evaluating numerical reasoning over text and tables.
yale-nlp/DocMath-Eval
dataset
Official repository for the survey, maintaining a categorized collection of papers, projects, datasets, tools, and related public materials.
OpenDataBox/awesome-data-llm
A curated repository of papers and benchmarks associated with the survey on reasoning with foundation models.
reasoning-survey/Awesome-Reasoning-Foundation-Models
Maintained repository containing the survey's paper list, figures, taxonomy-oriented table of contents, and contribution channel for adding omitted work.
UbiquitousLearning/Efficient_Foundation_Model_Survey
The authors' repository organizes VLM papers, models, datasets, evaluation resources, alignment methods, applications, and challenge areas beyond the static paper.
zli12321/Vision-Language-Models-Overview
Official repository for the survey, containing the README, poster, and datasets.csv catalog used to share the dataset analysis.
katesanders9/grounded-events
agentUniverse, a multi-agent ecosystem for autonomous agents.
agentuniverse-ai/agentUniverse
framework
Agno, described as an agentic workflow framework for LLM applications.
agno-agi/agno
framework
Phidata, described as a framework for building multi-modal agents with memory, knowledge, tools, and reasoning.
agno-agi/phidata
framework
Coze, described as an open framework for building agentic applications.
coze-dev/coze
framework
Flowise, described as a drag-and-drop UI to build LLM apps with LangChain.
FlowiseAI/Flowise
framework
LangGraph, described as a stateful multi-actor workflow library for LLM applications.
langchain-ai/langgraph
framework
Dify, described as an open-source LLM application development platform.
langgenius/dify
framework
Microsoft Semantic Kernel, compared as an agent workflow system.
microsoft/semantic-kernel
framework
n8n, described as a fair-code workflow automation platform with UI and integrations.
n8n-io/n8n
OpenAI Swarm, described as a multi-agent framework by OpenAI.
openai/swarm
framework
Qwen-Agent, a QwenLM agent framework/repository compared in the survey.
QwenLM/Qwen-Agent
framework
Official companion repository that organizes papers relevant to language-model data selection across the training stages and method categories used by the survey.
alon-albalak/data-selection-survey
Transformer model library used as an inference baseline in the framework comparison.
huggingface/transformers
Inference and deployment framework used in the paper's W4A16 quantization benchmark.
InternLM/lmdeploy
LLM serving framework compared for inference and serving throughput, memory management, batching, and scheduling.
ModelTC/lightllm
NVIDIA inference and serving framework used in the paper's W4A16 quantization benchmark and framework comparison.
NVIDIA/TensorRT-LLM
An author-linked repository organizing papers on retrieval-augmented generation.
USTCAGI/Awesome-Papers-Retrieval-Augmented-Generation
GPT Engineer, a software-development agent implementation cited in the engineering application survey and open-source project discussion.
AntonOsika/gpt-engineer
implementation
GPT Researcher, an experimental application that uses LLMs for research-question development, web crawling, source summarization, and aggregation.
assafelovic/gpt-researcher
implementation
AI Legion, an LLM-agent implementation cited in the survey's open-source library and reference set.
eumemic/ai-legion
implementation
LoopGPT, an LLM-agent implementation cited in the survey's open-source library and reference set.
farizrahman4u/loopgpt
implementation
AGiXT, an agent framework implementation cited in the survey as a dynamic AI automation platform.
Josh-XT/AGiXT
framework
DemoGPT, a software-development agent repository cited in the engineering application survey and open-source project discussion.
melih-unsal/DemoGPT
implementation
MiniAGI, an LLM-agent implementation cited in the survey's open-source library and reference set.
muellerberndt/mini-agi
implementation
AgentVerse, a multi-agent collaboration framework referenced among surveyed agent systems and open-source libraries.
OpenBMB/AgentVerse
framework
AgentGPT, an LLM-based autonomous-agent system cited in the survey's open-source library and reference set.
reworkd/AgentGPT
implementation
Auto-GPT, an autonomous LLM-agent implementation included in the construction taxonomy and open-source library discussion.
Significant-Gravitas/Auto-GPT
implementation
SmolModels/developer-style agent repository cited as a software engineering application artifact.
smol-ai/developer
implementation
WorkGPT, a workflow-oriented LLM-agent framework cited as similar to AutoGPT and LangChain.
team-openpm/workgpt
implementation
SuperAGI, an autonomous-agent framework cited in the survey's open-source library and reference set.
TransformerOptimus/SuperAGI
implementation
XLang, an LLM-agent/tool-use framework cited as supporting executable language grounding and interaction with databases, web applications, and physical robots.
xlang-ai/xlang
implementation
Curated repository for tracking LoRA-related research updates and supporting discussion around the survey taxonomy.
ZJU-LLMs/Awesome-LoRAs
Author-maintained repository established to facilitate ongoing updates and sharing of advances related to the survey's MoE literature coverage.
withinmiaov/A-Survey-on-Mixture-of-Experts-in-LLMs
Repository for the survey on memory mechanisms of LLM-based agents, including the paper link and visual summaries of the survey sections.
nuster1128/LLM_Agent_Memory_Survey
A curated reading list accompanying the survey, organized around LLM-agent optimization methods, datasets, benchmarks, and applications.
YoungDubbyDu/Awesome-LLM-Agent-Optimization-Papers
Repository for the paper's code and experimental workflow comparing LLM self-explanations, human rationales, and post-hoc attribution explanations.
oeberle/self_explanations_human_rationales
benchmark
Repository for CaMeL, a dual-LLM architecture with a safety execution layer and access-control policies for preventing data- and control-flow hijacking.
google-research/camel-prompt-injection
Repository for JailbreakBench, an evaluation framework for robustness against policy-violating behaviors and adversarial prompts.
JailbreakBench/jailbreakbench
benchmark
Repository associated with IsolateGPT, which isolates application execution and uses structured communication protocols between a planner and dedicated submodels.
llm-platform-security/SecGPT
Repository for Garak, a security-probing framework that generates and executes adversarial probes to assess LLM vulnerabilities.
NVIDIA/garak
Repository for NeMo Guardrails, cataloged as a programmable self-reflection/guardrail intervention.
NVIDIA/NeMo-Guardrails
Repository path listed as the source for the gas station revenue dataset.
bighuang624/DSANet
dataset
Repository listed as the source for daily COVID-19 confirmed and recovered case data.
CSSEGISandData/COVID-19
dataset
Repository listed as the source for SPMD and VED driving and vehicle energy datasets.
ElmiSay/DeepFEC
dataset
Repository listed as the source for the exchange-rate dataset used in LTSF studies.
laiguokun/multivariate-time-series-data
dataset
Repository listed as the source for daily stock opening price data.
z331565360/State-Frequency-Memory-stock-prediction
dataset
Repository listed as the source for the ETT transformer temperature/load dataset.
zhouhaoyi/ETDataset
dataset
Public repository containing the medical RAG application, evaluation framework, text rechunking pipeline, experimental configurations, and generated evaluation outputs associated with the study.
abdullahmoosa/medrag-research
OpenAI HumanEval benchmark for evaluating code generation with pass@k metrics.
openai/human-eval
dataset
Self-rewarding reasoning LLM implementation referenced as an example of using model-generated judgments to reduce annotation cost.
RLHFlow/Self-rewarding-reasoning-LLM
framework
AlpacaEval benchmark for automatic evaluation of instruction-following model outputs.
tatsu-lab/alpaca_eval
benchmark
Repository containing the Phase 1 SSL and contrastive encoder code, Phase 2 MoE PPO curriculum, inference and backtest scripts, routing diagnostics, and deployment-related components; the repository states that Phase 3 personalization is proprietary and not released.
rpishehv/PublicFinance-RL
framework
Repository containing code for training and evaluating the Transformer electricity price forecasting model and comparing it against EPF toolbox benchmarks.
osllogon/epf-transformers
benchmark
Repository linked from the paper that mirrors the paper title, abstract, framework figure, table of contents, and compiled relevant works for agent categories and attack types.
OSU-NLP-Group/AgentAttack
framework
Author-provided production-oriented implementation of the A-Mem agentic memory system.
WujiangXu/A-mem-sys
Author-provided repository for evaluating the A-Mem method and reproducing benchmark experiments.
WujiangXu/AgenticMemory
Open-source MVP and implementation repository for the AAGATE governance platform introduced by the paper.
kenhuangus/AAGATE
Repository for ABC-Bench, a benchmark for evaluating whether coding agents can explore repositories, edit code, configure environments, deploy containerized backend services, and pass external HTTP/API integration tests.
OpenMOSS/ABC-Bench
dataset
Optimized Faiss exact-search implementation for Intel CPUs.
architecture-research-group/ae-asplo25-iks-faiss
package
Cycle-approximate IKS simulator parameterized with RTL and memory/interconnect timing.
architecture-research-group/iks_simulator
system
Public repository containing the access-controlled website implementation, agent-side experiment scripts, modified SST/Auth component as a submodule, and experiment logs for delegated access workflows.
asu-kim/agentic-website
framework
Public repository for MCTSr, including scripts for running the supported mathematics benchmarks with LLM inference servers.
trotsky1997/MathBlackBox
Code and dataset repository for ActivationReasoning, including implementation and materials for replication or extension.
ml-research/ActivationReasoning
dataset
Official repository containing the FLARE code, task configurations, experimental data, retrieval setup, and run instructions.
jzbjyb/FLARE
Repository containing the ADAGE seven-stage construction pipeline, CAPR-ar/CAPR-am/CAPR-ja benchmark data, model-evaluation code, configurations, and reported evaluation results.
AhmedHajAhmed/adage-benchmark
dataset
Repository linked by the paper for AutoCompressor code and released models.
princeton-nlp/AutoCompressors
Repository containing data loaders, preprocessing, regime models, custom environments, PPO training pipelines, ablations, evaluation outputs, figures, and notebooks associated with the regime-aware portfolio framework.
GabrielNixon/RegimeAware-PPO
framework
SentiFin is cited as a benchmark dataset for sentiment analysis of Indian financial news headlines and is used to fine-tune the LLaMA 3.2 model.
pyRis/SEntFiN
dataset
An installable Python repository implementing AGoT, AIoT, and GIoT and providing experimental setups, datasets, and result files used to reproduce or inspect the paper's evaluations.
AgnostiqHQ/multi-agent-llm
framework
Repository containing the code developed and used for the study, with a README to support replication and methodology exploration.
stellacydong/rl-cvar-insurance-reserving
framework
GitHub repository identified by the paper as containing implementation details for the Dueling DDQN liquidity-provision method and baseline methods.
HaochenZhang717/Uniswap-v3
benchmark
Repository stated to include scripts for data preprocessing, model training, performance evaluation, and ablation studies for AMDTL.
mlaurelli/amdtl
framework
Repository containing AMDM implementation code, simulation scripts, evaluation scripts, example data, results files, plots, and the paper materials.
Manishms18/Adaptive-Multi-Dimensional-Monitoring
dataset
Longformer repository for the long-document transformer model evaluated as an additional architecture in the paper.
allenai/longformer
implementation
A continuously updated collection of FFM-related publications, tools, datasets, and resources associated with the survey.
FinFM/Awesome-FinFMs
The paper identifies this repository as containing representative Python code generated under the tested prompt levels.
VonAugustus/SnakeData
implementation
Author-owned repository for the ICME 2024 ATS paper and its proposed scene-text VQA architecture.
FrankZxShen/ATS
Repository implementing AFlow's nodes, operators, workflow representation, optimizer, evaluator, benchmark integrations, and scripts for reproducing the paper's workflow-search experiments.
FoundationAgents/AFlow
Claude-Agent-SDK framework used as one of the scaffold alternatives in the agentic scaffold impact study.
anthropics/claude-agent-sdk-python
framework
Public repository for the AgencyBench benchmark and evaluation toolkit released by the authors.
GAIR-NLP/AgencyBench
dataset
OpenAI-Agents-SDK framework used as one of the scaffold alternatives in the agentic scaffold impact study.
openai/openai-agents-python
framework
Repository for the AGENT KB cross-framework agent memory system introduced and evaluated in the paper.
OPPO-PersonalAI/Agent-KB
framework
Official open-source implementation of Agent Laboratory, including the end-to-end research workflow and source modules for mle-solver and paper-solver.
SamuelSchmidgall/AgentLaboratory
Official Agent Lumos repository containing code for annotation generation, module training, and benchmark evaluation.
allenai/lumos
Official WebShop environment used as an unseen interactive task in the Lumos generalization evaluation.
princeton-nlp/WebShop
benchmark
Repository for the Agent Mentor / Agent Analytics open-source observability and analytics platform for agentic AI applications.
AgentToolkit/agent-mentor
framework
GitHub path identified by the paper as the code corresponding to the analytics pipeline used for semantic feature analysis.
AgentToolkit/agent-mentor
implementation
Repository for building task/state knowledge, processing training data, constructing the state knowledge cache, LoRA training of agent and world knowledge models, and evaluating the paper's planning experiments.
zjunlp/WKM
Repository containing experiment code, response matrices, IRT models, task embeddings, LLM-as-a-judge features, adaptive testing code, and scripts for the new task, new response, new agent, and new benchmark experiments.
dariakryvosheieva/agent-psychometrics
implementation
Repository for the paper's virtual trading arena, ArenaTrader implementation, prompts, code, and data.
wekjsdvnm/Agent-Trading-Arena
dataset
Official code repository implementing AWM pipelines for WebArena and Mind2Web in offline and online settings.
zorazrw/agent-workflow-memory
Repository for the Agent-as-a-Judge project and DevAI-related evaluation artifacts.
metauto-ai/agent-as-a-judge
framework
GPT-Pilot is one of the three open-source code-generation agentic systems benchmarked in the paper.
Pythagora-io/gpt-pilot
framework
A GitHub repository collecting papers and resources for the survey on Agent-as-a-Judge.
ModalityDance/Awesome-Agent-as-a-Judge
Repository associated with Agent-R, the paper's iterative self-training framework for training language-model agents to reflect and recover from errors.
bytedance/Agent-R
framework
Repository for AgentBench datasets, environments, and integrated evaluation package.
THUDM/AgentBench
dataset
Official AgentBoard repository containing the benchmark/evaluation framework and associated data resources introduced by the paper.
hkust-nlp/AgentBoard
dataset
Indeed Hiring Lab repository tracking the share of job postings mentioning artificial intelligence.
hiring-lab/AI-Hiring-Tracker
dataset
Google's Agent-to-Agent Protocol repository, referenced as the source for A2A, one of the modern agent communication protocols compared in the paper.
google/A2A
implementation
BlenderMCP repository cited as a GitHub integration for Blender Model Context Protocol.
ahujasid/blender-mcp
implementation
PowerAgent PowerMCP repository cited as a GitHub implementation for power-system simulation software MCPs.
PowerAgent/PowerMCP
framework
Repository hosting the draft proteomics_GROUNDING.md epistemic grounding specification and Appendix A preliminary testing materials.
OmicsContext/proteomics-context
framework
LangGraph is used to illustrate graph traversal with persistent state, checkpoints, controlled cycles, guard nodes, approval steps, and typed state updates for production flow engineering.
langchain-ai/langgraph
implementation
Swarm is used to illustrate specialist-agent handoffs and routines as a controllable coordination pattern complementary to state-machine-style graph orchestration.
openai/swarm
implementation
Open-source repository for the Agent4CT loop, all 26 solver implementations, compact recombination solvers, helical-to-fan rebinning pipeline, and evaluation scripts.
akmaier/Agent4CT
benchmark
Agent-zero repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
agent0ai/agent-zero
framework
ANUS repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
anus-dev/ANUS
framework
Camel repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
camel-ai/camel
framework
CrewAI repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
crewAIInc/crewAI
framework
MetaGPT repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
FoundationAgents/MetaGPT
framework
Google ADK repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
google/adk-python
framework
Source code repository released by the authors for reproducing the benchmark comparison.
GPT-Laboratory/22-Agentic-Framework-Comparison-for-Reasoning-Tasks-across-BBH-GSM8K-and-ARC-Benchmarks
implementation
LangChain repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
langchain-ai/langchain
framework
LangGraph repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
langchain-ai/langgraph
framework
Mastra repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
mastra-ai/mastra
framework
PraisonAI repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
MervinPraison/PraisonAI
framework
Autogen repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
microsoft/autogen
framework
Semantic-kernel repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
microsoft/semantic-kernel
framework
TaskWeaver repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
microsoft/TaskWeaver
framework
OpenAI-Agents-Python repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
openai/openai-agents-python
framework
Swarm repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
openai/swarm
framework
Pydantic-AI repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
pydantic/pydantic-ai
framework
Qwen-Agent repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
QwenLM/Qwen-Agent
framework
AutoGPT repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
Significant-Gravitas/AutoGPT
framework
SuperAGI repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
TransformerOptimus/SuperAGI
framework
Upsonic repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
Upsonic/Upsonic
framework
Agency-swarm repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
VRSEN/agency-swarm
framework
BabyAGI repository evaluated as a selected agentic framework in the paper's 22-framework benchmark study.
yoheinakajima/babyagi
framework
A curated and continuously updated collection of papers and resources organized around the survey's foundational, self-evolving, collective, application, and benchmark taxonomy.
weitianxin/Awesome-Agentic-Reasoning
Code repository for the Agentic Reasoning framework introduced and evaluated in the paper.
theworldofagents/Agentic-Reasoning
framework
Public repository for Agentic Reward Modeling, including the RewardAgent implementation and materials intended to facilitate further research.
THU-KEG/Agentic-Reward-Modeling
system
A continuously updated collection of relevant studies for the Agentic Web.
SafeRL-Lab/agentic-web
Official code repository linked by the paper for Agentic-DPO; the current release includes the StableToolBench Qwen3.5-2B training pipeline, canonical step pairs, PPA rendering, hard-negative generation, and trainer code.
Schuture/Agentic-DPO
Repository for the AgenticPay benchmark and framework, including buyer and seller agents, negotiation environments, examples, metrics, and model backends for LLM-based commerce negotiation.
SafeRL-Lab/AgenticPay
dataset
Repository containing the AgentLAB benchmark code, attack scripts, environments, prompts, data, and usage instructions for evaluating LLM agents against long-horizon attacks.
TanqiuJiang/AgentLAB
dataset
Official open-source repository for the Agentless approach introduced and evaluated in the paper.
OpenAutoCoder/Agentless
implementation
Repository associated with AgentOrchestra; it contains the hierarchical agent runtime and evolving protocol/resource implementation used for general-purpose agent research.
SkyworkAI/DeepResearchAgent
Repository for the AgentRewardBench library, including tools for running agents, running judges, scoring judgments, loading trajectories, and submitting leaderboard results.
McGill-NLP/agent-reward-bench
dataset
Repository associated with AgentRx, the paper's diagnostic framework and benchmark artifact for AI-agent failure attribution.
microsoft/AgentRx
dataset
Official repository for PASB, including the benchmark data, baseline runners, judge code, audit scripts, and documentation.
henrymao2004/agent-sycophancy
dataset
Hermes-Agent is one of the two stateful personal-agent stacks evaluated by PASB.
NousResearch/hermes-agent
OpenClaw is one of the two stateful personal-agent stacks evaluated by PASB.
openclaw/openclaw
A curated GitHub repository associated with the paper that lists and classifies related papers on LLM-based agents in software engineering.
DeepSoftwareAnalytics/Awesome-Agent4SE
dataset
The GitHub repository for AgentScope, the multi-agent platform described in the paper.
modelscope/agentscope
framework
Public implementation of AgentStepper and relevant data for the paper's evaluation.
sola-st/AgentStepper
dataset
GitHub Gist containing the Claude Code implementation prompt for the case summarization by file name microservice.
https:/
GitHub Gist containing the Case Summarization by Given Case Name Workflow pitch generated by the Planning Agent.
https:/
Official repository for the AgentVerse framework introduced and evaluated in the paper.
OpenBMB/AgentVerse
AgentWard prototype repository implementing a lifecycle security architecture for autonomous AI agents with native adaptation to OpenClaw.
FIND-Lab/AgentWard
framework
Agile V skills repository v1.3, described as the composable AI-agent skills library that operationalizes Agile V and includes context-engineering patterns.
Agile-V/agile_v_skills
framework
Repository released by the authors for the robust-transformers implementation used with AGRO.
bhargaviparanjape/robust-transformers
framework
A GitHub CLI extension that exposes a compact interface for reading review threads and submitting inline pull request comments.
agynio/gh-pr-review
implementation
Agyn platform for configuring and orchestrating multi-agent systems with explicit communication, roles, and dedicated sandboxes.
agynio/platform
framework
Repository for the AI Act Evaluation Benchmark, including structured EU AI Act compliance scenarios, QA pairs, documentation, and scripts.
davidath/ai-act-evaluation-benchmark
dataset
Official repository released by the authors with code to reproduce all experimental results, implementations of the proposed simple baselines, and the DSPy joint optimizer.
benediktstroebl/agent-evals
BabyAGI is used as a representative agentic framework showing how LLMs can be embedded in feedback loops to plan, act, adapt, and manage or prioritize subtasks.
yoheinakajima/babyagi
framework
Repository for the violent-python dataset of security-oriented Python code and natural-language descriptions.
dessertlab/violent-python
dataset
Repository for CodeBERT, the pre-trained programming-language model used as the fine-tuned open-model baseline.
microsoft/CodeBERT
implementation
Repository containing an implementation related to reproducing 'Clustering by fast search and find of density peaks'.
AIReproducibility2018/ClusteringByFastSearchAndFindOfDensityPeaks
implementation
User interface and implementation for customizing the visual framework to empirical studies using AI accuracy, human adherence, and final decision-making accuracy, and for computing reliance components and Q.
jhnnsjkbk/accuracy-reliance
implementation
Official open-source repository for Denario, a modular multi-agent system for scientific research assistance that supports idea generation, literature checking, planning, code execution, analysis, paper drafting, and review.
AstroPilot-AI/Denario
A GitHub Action that reviews pull requests by sending changed file contents to ChatGPT/OpenAI and posting review comments back to the PR.
agogear/chatgpt-pr-review
system
Repository containing the paper's algorithm code and a link to the associated QuantConnect backtest artifact.
tiagomonteiro0715/AI-Powered-Energy-Algorithmic-Trading-Integrating-Hidden-Markov-Models-with-Neural-Networks
implementation
Repository released by the authors for the Writing Quality benchmark, WQRM models, data, and associated evaluation or editing code.
salesforce/creativity_eval
GitHub repository linked by the paper for example Jupyter notebooks and materials related to AIDev and AI teammates in SE 3.0.
SAILResearch/AI_Teammates_in_SE3
dataset
Repository for the AIRepr / LLM data-science reproducibility experiments and code released by the authors.
qunhualilab/LLM-DS-Reproducibility
framework
Repository stated by the paper as the public code and data release for AirQA.
OpenDFM/AirQA
dataset
Repository for the AISysRev web application, an LLM-based tool for title-abstract screening that imports CSV metadata, applies inclusion/exclusion criteria using multiple LLMs, supports manual screening with LLM guidance, and exports results to CSV.
EvoTestOps/AISysRev
system
Repository containing ALFRED dataset tooling, data-generation and replay code, Seq2Seq baseline training/evaluation code, documentation, and benchmark submission utilities.
askforalfred/alfred
dataset
Official ALFWorld repository containing the aligned environments, downloadable game/PDDL assets, pretrained components, agents, and training/evaluation code.
alfworld/alfworld
implementation
A curated repository accompanying the paper that organizes embodied-AI papers and resources covered by the survey.
HCPLab-SYSU/Embodied_AI_Paper_List
Contains the source code, dataset-construction scripts, dependency documentation, and result-generation pipelines associated with the paper.
brains-group/FLARKO
framework
Repository containing code and configurations for training and evaluating AlphaDPO.
junkangwu/alpha-DPO
implementation
Official Alympics repository containing the framework code, Water Allocation Challenge experiment code, requirements, prompts/resources, and related implementation materials.
microsoft/Alympics
Repository containing the AMVICC prompt CSV, model-evaluation scripts, image-generation scripts, result examples, and utilities used to reproduce or extend the benchmark experiments.
AahanaB24/AMVICC
benchmark
Repository containing a practical implementation of the online AdaVol recursive volatility-prediction method.
nicklaswerge/AdaVol
package
Public repository containing experimental code supporting the TDQN trading results reported in the paper.
ThibautTheate/An-Application-of-Deep-Reinforcement-Learning-to-Algorithmic-Trading
benchmark
Official repository for the paper's uncertainty analysis, ConfiLM resources, and Olympic 2024 data release.
hasakiXie123/LLM-Evaluator-Uncertainty
Semantic Kernel is described as a modular, plugin-based framework for integrating LLM and agent capabilities into enterprise and software systems.
microsoft/semantic-kernel
framework
Swarm is described as a lightweight multi-agent interface framework for experimenting with multi-agent coordination.
openai/swarm
framework
BabyAGI is described as an experimental framework for autonomous task planning and iterative execution through a self-improving task loop.
yoheinakajima/babyagi
framework
Author-provided Deformable DETR code repository used for the reconstruction-based SSL evaluation.
gokulkarthik/Deformable-DETR
implementation
Author-provided DETR code repository used for the proposed SSL task experiments.
gokulkarthik/detr
implementation
Official SWE-bench experiment repository used by the authors as the source of execution logs, generated patches, and pass/fail statuses for the studied tools.
SWE-bench/experiments
dataset
Code repository for ACEFormer, the attention-based stock forecasting system introduced by the paper.
DurandalLee/ACEFormer
implementation
Repository for the Online-Mind2Web benchmark and associated evaluation artifacts introduced by the paper.
OSU-NLP-Group/Online-Mind2Web
dataset
Google Research repository containing Vision Transformer code, fine-tuning support, and released pretrained models associated with the paper.
google-research/vision_transformer
implementation
GPT Engineer is described as an AI coding agent that can generate an entire codebase from a prompt and ask clarifying questions.
AntonOsika/gpt-engineer
implementation
MetaGPT is described as a multi-agent framework assigning different GPT roles to form a collaborative software entity for complex tasks.
geekan/MetaGPT
framework
AgentGPT is described as a framework for rapidly configuring and deploying autonomous AI agents.
reworkd/AgentGPT
framework
Multi-GPT is described as an experimental multi-agent system in which expertGPTs collaborate, communicate, and use short- and long-term memory.
sidhq/Multi-GPT
system
Auto-GPT is described as an early example of GPT-4 running fully autonomously by chaining LLM thoughts to achieve user-set goals.
Significant-Gravitas/Auto-GPT
implementation
SuperAGI is described as a developer-centric open-source framework for building, managing, and running autonomous AI agents.
TransformerOptimus/SuperAGI
framework
BabyAGI is described as a task-driven autonomous AI agent that builds and prioritises tasks toward an overall goal.
yoheinakajima/babyagi
implementation
A curated repository of reentrancy attacks from which the paper draws 13 sufficiently isolated real-world exploit contracts for evaluation.
pcaversaccio/reentrancy-attacks
dataset
Official implementation of the paper's lightweight contamination detector, including search scripts, contamination reports for six benchmarks, model predictions, clean-dirty comparison code, and visualizations.
liyucheng09/Contamination_Detector
Repository containing code to generate school-level mathematical question-answer pairs and access the released Mathematics Dataset used for the paper's benchmark experiments.
deepmind/mathematics_dataset
dataset
The report states that EnglandCovid is a PyTorch Geometric Temporal dataset and cites this GitHub repository as reference [9].
benedekrozemberczki/pytorch_geometric_temporal
dataset
Repository referenced by the paper for more details on the EnglandCovid dataset conversion and temporal neural network analysis.
verma-rishu/Analysis_TNNs
implementation
A repository of DAN-style jailbreak prompts represented in the paper's attack-source comparisons.
0xk1h4n/DAN-Jailbreak
A system-prompt leak collection used to inform the paper's adversarial prompt pool.
asgeirtj/system_prompts_leaks
A public collection of GPT super-prompts used as part of the paper's heterogeneous attack-source pool.
CyberAlbSecOP/Awesome_GPT_Super_Prompting
An implementation reference for the self-examination or self-defence mechanism evaluated by the paper.
poloclub/llm-self-defence
A prompt-injection defence framework used as the reference point for vector-based detection and filtering.
protectai/rebuff
A curated jailbreak-prompt repository used to broaden the study's community-sourced attack collection.
Techiral/awesome-llm-jailbreaks
A defence repository referenced for the voting and structured validation approaches discussed and evaluated.
theshi-1128/llm-defence
A prompt-hacking resource used as one of the repositories from which attack examples were collected.
TrustAI-laboratory/Learn-Prompt-Hacking
A prompt-hacking collection used as an external source of attack patterns.
yunwei37/prompt-hacker-collections
Repository released with the paper containing the additional human reference translations and related analysis resources.
facebookresearch/analyzing-uncertainty-nmt
The fairseq-py toolkit supplies the pretrained convolutional sequence-to-sequence models used as the main objects of analysis.
facebookresearch/fairseq-py
A curated repository for the paper's agentic-memory survey, organised around the taxonomy introduced in the manuscript and intended to be updated as the field evolves.
FredJiang0324/Anatomy-of-Agentic-Memory
Official repository for the paper, containing a CLAIR preference-generation notebook, cached results, documentation, and links to associated data.
ContextualAI/CLAIR_and_APO
Repository for the AndroidWorld environment, task suite, evaluation logic, and associated experiments introduced by the paper.
google-research/android_world
dataset
Official API-Bank code and data directory containing implemented APIs, datasets, database initialization resources, evaluators, simulators, examples, and demo code.
AlibabaResearch/DAMO-ConvAI
dataset
GitHub repository for the DLS-DDPG implementation used or released with the paper.
Hisato-Komatsu/DLS-DDPG
implementation
Repository for AppWorld Engine and AppWorld Benchmark, including the simulated app environment, benchmark tasks, and evaluation infrastructure.
stonybrooknlp/appworld
dataset
Repository for APTBench, the benchmark for evaluating agentic potential of base LLMs during pre-training.
TencentYoutuResearch/APTBench
dataset
Repository identified by the paper as the code for the Arabic tool-calling benchmark work.
kubrak94/gorilla
dataset
AutoResearchClaw is cited as an example of the scenario-verticalized or research-oriented pattern and as the only pipeline/stage subagent case.
aiming-lab/AutoResearchClaw
framework
deer-flow is cited as an example of the scenario-verticalized or research-oriented pattern.
bytedance/deer-flow
framework
cline is included as a corpus project and cited as an example of tool-based delegation.
cline/cline
system
docker-agent is used as a representative orchestration-oriented project combining orchestrator-worker structure, hybrid context, MCP-first tooling, and advanced execution controls.
docker/docker-agent
system
fast-agent is used as an illustrative project showing tool delegation, hybrid context handling, and MCP-first tool registration.
evalstate/fast-agent
framework
Gemini CLI is included as one of the official or first-party products from major AI companies in the corpus.
google-gemini/gemini-cli
system
deepagents is cited as an example of the scenario-verticalized or research-oriented pattern.
langchain-ai/deepagents
framework
Mistral Vibe is included as one of the official or first-party products from major AI companies in the corpus.
mistralai/mistral-vibe
system
Kimi CLI is included as one of the official or first-party products from major AI companies in the corpus and is named as a balanced CLI representative.
MoonshotAI/kimi-cli
system
nullclaw is cited as an example of the Enterprise Full-Featured pattern.
nullclaw/nullclaw
framework
codex is included as an official product/public-evidence case in the corpus and appears in the complete project list.
openai/codex
system
OpenClaw is analyzed as a corpus project and cited as an example of multi-level recursive or balanced CLI-style infrastructure depending on context.
openclaw/openclaw
framework
OpenHands is included in the 70-project corpus and used as an example of event-driven, hybrid-context, enterprise-tool, advanced-safety infrastructure.
OpenHands/OpenHands
framework
agentpool is used to illustrate event-driven subagent architecture with hierarchical context, registry tooling, and enterprise safety classification.
phil65/agentpool
framework
Qwen Code is included as one of the official or first-party products from major AI companies in the corpus.
QwenLM/qwen-code
system
openfang is cited as an example of the Enterprise Full-Featured pattern.
RightNow-AI/openfang
framework
Repository containing three customer-service chatbot variants generated from different single prompts, with methodology, prompts, and source code for the paper's vibe-architecting demonstration.
phomarkon/vibe-architecting-case-study
implementation
GitHub repository for the ARDNS-FN-Quantum code, including the core script and interactive analysis or visualization notebook described by the paper.
umbertogs/ardns-fn-quantum
framework
Repository containing NeuLR and the paper's appendix or supporting resources for benchmark construction and evaluation.
DeepReasoning/NeuLR
dataset
LongBench is used as the main benchmark source for most datasets and for baseline evaluation settings.
THUDM/LongBench
dataset
GitHub repository for the Cross-Attention-only Time Series transformer introduced in the paper.
dongbeank/CATS
benchmark
Repository containing the code implementation for evaluating language models using the paper's framework and generating visualizations; described as configurable for other HuggingFace models, metrics, task types, domains, and reasoning types.
neelabhsinha/lm-application-eval-kit
benchmark
Official repository for MMStar containing the evaluation code and dataset associated with the paper.
MMStar-Benchmark/MMStar
dataset
Repository containing code for ArgEval, the paper's argumentation-based LLM decision-support framework.
adamdejl/argeval
framework
The core open-source implementation repository for the Ark robotics framework introduced by the paper.
Robotics-Ark/ark_framework
Salesforce repository containing the Art_or_Artifice project folder and associated creativity-evaluation resources.
salesforce/creativity_eval
benchmark
Code repository linked by the paper for the ART framework and its language-program implementation.
bhargaviparanjape/language-programmes
implementation
Companion repository assembled by the authors to collect the papers surveyed in the review and link associated code when available.
dengjianyuan/Survey_AI_Drug_Discovery
Repository containing Python implementation files and supplementary materials for detecting hallucinations with specialized model divergence.
ACMCMC/ask-a-local
implementation
Repository reported by the authors as containing the code and data for Ask an Expert / BBMHReasoning experiments.
QZx7/BBMHReasoning
implementation
Repository containing code and scripts for the ASPIRE paper, including captioning, GPT-4 prompt use, spurious object detection, diffusion fine-tuning, image generation, and classifier training workflows.
Sreyan88/ASPIRE
framework
Repository released to support reproduction and continued evaluation of prompt-injection attacks and defenses studied in the paper.
sherdencooper/prompt-injection
Repository implementing Wanda/SNIP-based pruning, safety-utility set difference, ActSVD low-rank removal, orthogonal-projection rank disentanglement, zero-shot utility evaluation, and attack evaluation for Llama2-chat models.
boyiwei/alignment-attribution-code
Repository containing the ARMT implementation and scripts for training and evaluating the architecture studied in the paper.
RodkinIvan/associative-recurrent-memory-transformer
implementation
Official repository for ATACompressor, containing pretraining, finetuning, inference, preprocessing, configuration, and LoRA implementation code.
Cocobalt/ATACompressor
Tensor2Tensor repository containing the code used by the authors to train and evaluate the Transformer models.
tensorflow/tensor2tensor
Repository linked by the authors as the code for the attention-retention continual-learning framework.
zugexiaodui/AttentionRetentionCL
framework
Repository released by the authors containing system responses and their human and automatic attribution ratings for the Attributed QA study.
google-research-datasets/Attributed-QA
Official Audio-Omni repository containing the model implementation, inference code, API, prompts, interface, configuration, and setup instructions.
ZeyueT/Audio-Omni
Repository linked from the arXiv v1 project page and identified in its README as the official repository for the AudioDER paper, with dataset access and construction resources.
anonycode26/AudioDER
dataset
Author-referenced sample dataset of synthetic identification-document images covering five document types.
meetsandesh/identification_document_dataset
dataset
Author-referenced repository for generating synthetic document images used in the document identification and information extraction experiment.
meetsandesh/synthetic_document_generator
dataset
Repository containing the implementation of Document Augmentation for dense Retrieval (DAR).
starsuzi/DAR
implementation
Repository identified by the paper as the official source-code location for the Auto-ADMET method.
alexgcsa/auto-admet
system
Repository containing the Auto-FP benchmark resources, including code, datasets, meta-features, and comprehensive experimental results associated with the paper.
AutoFP/Auto-FP
dataset
Official AutoAct repository containing code and prompts for self-instruct data generation, automatic tool selection, trajectory synthesis and filtering, LoRA-based self-differentiation, and group-planning evaluation.
zjunlp/AutoAct
Source-code repository for the AutoFlow framework introduced by the paper.
agiresearch/AutoFlow
framework
Repository for the Autoformer model and experiments introduced in the paper.
thuml/Autoformer
benchmark
The paper's AutoGen framework repository for building LLM applications via multi-agent conversations.
microsoft/autogen
framework
Repository for Bias Identification Test in Sentiments, including data files and templates for probing sentiment and toxicity models for bias; the paper specifically uses the disability facet.
PranavNV/BITS
dataset
Repository for the ADAS codebase introduced by the paper, including the Meta Agent Search implementation and experimental framework.
ShengranHu/ADAS
framework
Repository for ECLAIR, described as enterprise-scale AI for workflows, including code and scripts for the paper experiments and hospital workflow demo materials.
HazyResearch/eclair-agents
framework
Repository containing folders for datasets, models, plots, pretrained models, additional tests, requirements, and a README with benchmark results for AutoML-DC.
MilanShao/AutoML-for-Multi-Class-Anomaly-Compensation-of-Sensor-Drift
dataset
Open-source implementation of the paper's three-task validation case study, including Python orchestration, generated Prolog programs, Prolog templates, sample-data creation, and logic execution.
cecilpang/autobus-paper
Official repository for the AG3D museum model, exploration data, and PointNav++ benchmark artifacts.
aimagelab/ag3d
Official implementation and pretrained models for the impact-driven exploration method developed in Chapter 3.
aimagelab/focus-on-impact
Official LoCoNav implementation and models for deploying a Habitat-trained navigation system on a real LoCoBot.
aimagelab/LoCoNav
Official artifact for the Spot the Difference task, manipulated-map dataset, training code, and pretrained models.
aimagelab/spot-the-difference
dataset
Supplementary repository containing datasets, generated manuscripts, run records, coding runs, and supplemental appendix materials used to support the paper's evaluation.
rkishony/data-to-paper-supplementary
dataset
Code implementation of the data-to-paper framework for backward-traceable AI-driven scientific research.
Technion-Kishony-lab/data-to-paper
framework
Hosts the working paper, data.json, figures, tables, and an interactive visualization of Top-N portfolio performance and alpha concentration.
mapledust0/AI-Stock-Nowcasting
dataset
Idea2Paper repository for connecting research ideation to paper-oriented production.
AgentAlphaAGI/Idea2Paper
Aider repository for agent-assisted code editing and executable software workflows.
Aider-AI/aider
OpenScholar repository for literature-grounded scientific question answering and knowledge synthesis.
AkariAsai/OpenScholar
Tongyi DeepResearch repository for agentic deep-research workflows.
Alibaba-NLP/DeepResearch
OpenHands repository for general software-agent execution over files, tools, and runtimes.
All-Hands-AI/OpenHands
GPT Researcher repository for automated deep-research report generation.
assafelovic/gpt-researcher
ScienceClaw repository for scientific-agent workflow orchestration.
beita6969/ScienceClaw
DeerFlow repository for deep-research workflow orchestration.
bytedance/deer-flow
PaperQA2 repository for paper-grounded question answering and scientific synthesis.
Future-House/paper-qa
AI-Researcher repository for an integrated literature, experimentation, and reporting workflow.
HKUDS/AI-Researcher
autoresearch repository for a steerable software-native AI research loop.
karpathy/autoresearch
Open Deep Research repository for recursive literature research and report construction.
langchain-ai/open_deep_research
Agent Laboratory repository for a human-piloted multi-agent computational research workflow.
SamuelSchmidgall/AgentLaboratory
STORM repository for retrieval-grounded, multi-perspective long-form synthesis.
stanford-oval/storm
SWE-agent repository for repository-level software-agent execution.
SWE-agent/SWE-agent
ARIS repository for long-running AI research orchestration and execution.
wanshuiyin/Auto-claude-code-research-in-sleep
ResearchClaw repository for reusable research-agent workflow infrastructure.
ymx10086/ResearchClaw
Official repository for AvaTaR with implementation, configurations, data preparation, retrieval-task scripts, and baseline/evaluation code.
zou-group/avatar
dataset
Official source repository for the AVISE framework and the Red Queen SET introduced and evaluated in the paper.
ouspg/AVISE
Official AxQM repository containing the benchmark task statements, finite-dimensional quantum-mechanics library, Mathlib fork, per-task proof-length estimates, task-dependency ledger, and grading and submission scripts.
Axiomatic-AI/AxQM
benchmark
Repository for the summarize-from-feedback / TL;DR data used as one of the paper's two primary preference-learning evaluation settings.
openai/summarize-from-feedback
dataset
Repository for the BacktestBench benchmark and AutoBacktest implementation, including project folders for AutoBacktest, datasets, figures, tables, environment setup, database setup, and reproduction scripts.
jensenw1/BacktestBench
dataset
Repository for the BadAgent attack on LLM agents.
DPamK/BadAgent
implementation
Repository for the BagStacking implementation provided by the authors within a Scikit-learn API framework.
SeffiCohen/BagStacking
package
AgentGPT is analysed as a general-purpose autonomous LLM-powered multi-agent system with user-guided alignment in selected aspects such as decomposition, agent generation, and resource utilization.
reworkd/AgentGPT
framework
Auto-GPT is analysed as a general-purpose autonomous LLM-powered multi-agent system with autonomous goal decomposition, task action management, and resource utilization.
Significant-Gravitas/Auto-GPT
framework
SuperAGI is analysed as a general-purpose autonomous LLM-powered multi-agent system with some user-guided alignment options for agent-related and resource-related aspects.
TransformerOptimus/SuperAGI
framework
BabyAGI is analysed as a general-purpose autonomous LLM-powered multi-agent system with a profile similar to Auto-GPT across many assessed aspects.
yoheinakajima/babyagi
framework
The fairseq BART directory provides the implementation interface, released BART checkpoints, and task-specific usage and fine-tuning instructions associated with the paper.
facebookresearch/fairseq
Official repository for the BeaverTails dataset family, dataset cards, QA-moderation training/evaluation code, and links to released model/data artifacts.
PKU-Alignment/beavertails
dataset
Repository for General AgentBench, the unified benchmark and evaluation framework for general LLM agents.
cxcscmu/General-AgentBench
benchmark
Official repository for the WorfBench benchmark, WorfEval evaluation implementation, data, and experiment code.
zjunlp/WorfBench
dataset
Repository containing code for evaluating MT-BaxBench and MT-SECCODEPLT, the two splits of the MT-Sec evaluation kit.
JARVVVIS/mt-sec
benchmark
OpenAI Codex CLI, cited as a lightweight coding agent running in a terminal and evaluated as one of the agent scaffolds.
openai/codex
Chapyter is one of the data science agent frameworks benchmarked by DSEval.
chapyter/chapyter
Jupyter-AI is one of the agent frameworks benchmarked by DSEval.
jupyterlab/jupyter-ai
Official repository for DSEval, including the evaluation toolkit, benchmark data, results, and scripts.
MetaCopilot/dseval
dataset
Open-source Code Interpreter API implementation directly evaluated as a data science agent framework.
shroominic/codeinterpreter-api
rllab, the framework released with the paper containing the continuous-control tasks and reference implementations of the evaluated reinforcement-learning algorithms.
rllab/rllab
benchmark
Official repository for the paper's ECG foundation-model benchmark, including evaluation code, preprocessing/configuration assets, and the ECG-CPC framework with checkpoint links.
AI4HealthUOL/ecg-fm-benchmarking
benchmark
GitHub repository for the FaithJudge leaderboard and associated faithfulness evaluation resources.
vectara/FaithJudge
benchmark
Repository containing the modular benchmarking framework, configurations, scripts, results, and visualization code for comparing retrieval strategies in biomedical RAG.
deviprasadbal/RAGHealthcareRetrievalStrategies
benchmark
Repository for MedRag, the toolkit implementing the corpora, retrievers, and LLM configurations used in the study.
Teddy-XiongGZ/MedRAG
Repository for Mirage, the medical RAG evaluation benchmark introduced in the study.
Teddy-XiongGZ/MIRAGE
benchmark
Repository containing corruption scripts, model-evaluation code, sample execution materials, and links to reduced, corrupted, and verified DUDE and MPDocVQA benchmark data.
DavideNapolitano/VRD-UQA
dataset
Repository containing the agent scaffold, behaviour-analysis pipeline, SFT recipes, scripts, utilities, and evaluation suite associated with Behavior Priming for agentic search.
cxcscmu/Behavior-Priming-for-Agentic-Search
system
Repository containing the authors' BERT-of-Theseus implementation, GLUE scripts, compression examples, and links/instructions for the released MNLI-compressed model.
JetRunner/BERT-of-Theseus
Repository released by the authors with TensorFlow code for BERT, pretrained BERT_BASE and BERT_LARGE checkpoints, and scripts for replicating major fine-tuning experiments.
google-research/bert
Repository for reproducing and extending the paper's generator-versus-classifier experiments; it includes the main experiment script, a shell runner, and data files containing synthetic and human-labelled examples.
kinit-sk/multilingual-classifiers-not-generators
Official implementation and pretrained sample model for the paper's learned reference-free summary reward, including metric comparison and reward-training scripts.
yg211/summary-reward-no-reference
Official LEAP implementation containing the Python package, prompts, configuration files, data-processing scripts, SFT and DPO training scripts, and evaluation workflows for ALFWorld and WebShop, with InterCode-related code also included in the repository structure.
sanjibanc/leap_llm
Repository by genai-analytics containing a beyond-black-box-benchmarking folder with benchmark, core, examples, and sdk subfolders.
genai-analytics/publications
dataset
ParlAI crowdsourcing code associated with the paper's multi-session model-chat human evaluation.
facebookresearch/ParlAI
ParlAI implementation for loading and evaluating the Multi-Session Chat and PersonaSummary tasks introduced by the paper.
facebookresearch/ParlAI
dataset
Code repository identified by the paper for implementing the CRS reliability-evaluation framework.
rohitsalla/CRS
Official ICML 2023 implementation of DAC, including feature extraction, KNN-score computation, calibration code, experiment scripts, checkpoints, and a CIFAR-10/ResNet18 reproduction workflow.
futakw/DensityAwareCalibration
Official codebase containing 1dCA data generation, evaluated model implementations, ACT variants, training scripts, evaluation pipelines, and experiment configurations.
RodkinIvan/associative-recurrent-memory-transformer
benchmark
The LM Evaluation Harness supplies the raw, token-normalized, and character-normalized full-sequence scoring methods evaluated by the paper.
EleutherAI/lm-evaluation-harness
OpenCompass is one of the two evaluation frameworks whose multiple-choice scoring implementation is analyzed and empirically compared.
open-compass/opencompass
Code repository for Multi-Objective Direct Preference Optimization and its experimental workflow.
ZHZisZZ/modpo
implementation
Repository backing the Agentic Factor Investing project homepage, containing a README, project-framework image, interactive site, and chart data; it is a showcase rather than a complete research-code release.
allenh16/agentic-factor-investing
framework
GoodAI baseline LTM system using a vector database and JSON scratchpad to augment an LLM controller.
GoodAI/goodai-ltm
system
Versioned branch of the GoodAI LTM Benchmark repository containing code, test definitions, experiments, result data, and reports corresponding to the paper.
GoodAI/goodai-ltm-benchmark
dataset
Public repository containing RAG, GRAG, AGRAG, and HRAG prompts; text-to-Cypher and Cypher-to-QA prompts; few-shot query examples; guided-question generation material; the LLM-as-a-Judge rubric; the annual CTI report used for guided questions; and experiment logs.
ait-cti/beyond-vanilla-rag
benchmark
Code for f-DPO with reverse KL, forward KL, Jensen-Shannon, and alpha-divergence regularization, including scripts for IMDB, Anthropic HH, MT-Bench, PPO comparisons, and calibration experiments.
alecwangcq/f-divergence-dpo
implementation
Repository containing the code associated with the Strategic Tactical Agent Reasoning benchmark and its execution framework.
star-nexus/star
Repository containing the paper's experiments and results for the Agent Assessment Framework.
sa4s-serc/asf
benchmark
Repository containing BIG-bench task definitions, JSON and programmatic evaluation infrastructure, documentation, model score files, BIG-bench Lite resources, and contribution workflows.
google/BIG-bench
dataset
Repository for the paper's supplemental materials, including the coding schema, all repository metadata, raw graph data, and the LLM coding prompt.
ShaokangJiang/cursorrule-supp
dataset
TokenScope is used to extract probabilities for the first decision token where the judge commits to A or B.
Amirresm/tokenscope
package
Repository for the semantic-uncertainty method used as a hallucination-detection baseline.
lorenzkuhn/semantic_uncertainty
One of the two chest-X-ray datasets combined to construct the paper's four-class federated-learning evaluation corpus.
agchung/Figure1-COVID-chestxray-dataset
dataset
Official BookSum repository containing data-preparation, collection, cleaning, chapterization-support, and paragraph-alignment scripts associated with the paper.
salesforce/booksum
dataset
Repository containing the MuseD evaluation code and associated research artifact.
zhangyipin/mused
dataset
PyTorch implementation of BoostMIS with active-learning components, configuration files, training code, and released MESCC ResNet-50 feature and label artifacts.
wannature/BoostMIS
Official PyTorch implementation of BOSS for simulated ALFRED experiments associated with the paper.
clvrai/boss
framework
Repository for the paper containing the agent and AI2THOR environment code, experiment entry points, generated production rules and weights, prompts, world-knowledge database, bootstrapping/test logs, experiment spreadsheet, and token-usage figure.
zfy0314/cognitive-agents
Project repository for the paper's automated peer-review vulnerability evaluation and adversarial robustness study.
Lin-TzuLing/Breaking-the-Reviewer
benchmark
Official repository providing BridgeData V2 data-processing utilities, JAX implementations for several paper methods, training scripts, evaluation scripts, and links to checkpoints and robot setup resources.
rail-berkeley/bridge_data_v2
dataset
Repository containing preprocessing, KG demos, lab-informed pretraining, diagnosis and heart-failure training scripts, metrics, and notebooks for the DuaLK framework.
humphreyhuu/DuaLK
Implementation used to generate the saliency-map explanations that formed the H2 baseline condition.
greydanus/visualize_atari
The gym-sokoban implementation that the authors modified into Sokoban-switch and Sokoban-cells variants for precondition and cost-explanation experiments.
mpSchrader/gym-sokoban
An aggregated dataset of chess opening names and move sequences used by the paper to create opening-position concept datasets.
lichess-org/chess-openings
dataset
Companion agent layer containing Brain Researcher skills, agent templates, MCP adapters, and AutoResearch evaluation rubrics.
brain-researcher/brain-researcher-agent-kit
Public Brain Researcher implementation including the Python package, CLI, agent runtime, MCP server with versioned tool contracts, orchestrator, web UI, and deployment recipes.
brain-researcher/brain-researcher-public
Analysis code, specification ledger, per-hypothesis outputs, run report, and figures for the NeuroMark schizophrenia collaborator case evaluated in the paper.
XinhuiLi/BR-NeuroMark
Source-code repository for the BCDA study and its algorithmic experiments.
ShironT/bcda
implementation
Code for fitting and extrapolating BNSLs, reproducing the 4-digit-addition experiments and noiseless simulation in Figure 5, and decomposing BNSL into the power-law segments shown in Figure 1.
ethancaballero/broken_neural_scaling_laws
Repository for downloading/decrypting benchmark data, building or downloading indexes, running supported search agents, evaluating end-to-end and retrieval-only results, reproducing experiments, and integrating custom retrievers.
texttron/BrowseComp-Plus
benchmark
Source code for the CoELA framework and the paper's TDW-MAT and C-WAH experimental implementations, including LLM-agent code and experiment scripts.
UMass-Embodied-AGI/CoELA
OpenDev, the open-source command-line AI coding agent whose architecture, harness, context engineering, tool system, and lessons learned are described in the paper.
opendev-to/opendev
framework
Open-source Python package calibrated-explanations, including code repository, examples, notebooks, and evaluation/regression scripts for reproducing experiments.
Moffran/calibrated_explanations
package
Repository containing CPR, reset-method baselines, continual-learning environments, experiment configurations, plotting scripts, dependency specifications, and reproduction instructions.
LucMc/continual-learning
Repository containing experiment data, model configurations, prediction scripts, calibration implementations for agreement/entropy/FSD and baselines, evaluation scripts, scores, and visualization utilities.
veronica320/Calibrating-LLMs-with-Consistency
implementation
Repository containing installation instructions, data preparation, experiment scripts, evaluation code, and analysis for the paper's calibration framework.
kkkevinkkkkk/calibration
Source code accompanying the paper, with scripts for decoding, extracting internal-consistency information, and evaluating self-consistency variants.
zhxieml/internal-consistency
implementation
The open-source CAMEL library introduced by the paper, including agent implementations, prompts, data-generation pipelines, analysis tools, examples, and links to generated datasets.
camel-ai/camel
Repository designated by the paper for code, training conditions, and experimental run records.
basetenlabs/cortex
JSON benchmark file for the paper's freelance-style task suite.
reveondivad/certify
dataset
Repository for the Econometrics-Agent/MetricsAI system that automates econometric analysis through an AI-agent workflow and domain-specific econometric tools.
HKU-Business-AI-Center/Econometrics-Agent
framework
Official repository directory containing the paper's code, data, and experimental setup for writing alignment through edits.
salesforce/creativity_eval
Repository accompanying the paper, containing the ageval evaluator package, agent tools, baseline evaluators, datasets/labels, experiment configurations, notebooks, and a Gradio app for inspecting annotator outputs.
apple/ml-agent-evaluator
framework
Official repository containing 50 author-specific writing prompts and anonymized JSON evaluation data organized by quality versus style, prompting versus fine-tuning, and expert versus lay judges.
tuhinjubcse/GoodWritingBeGenerative
dataset
Repository linked by the paper as the available code for evaluating GPT models on mock CFA exams.
e-cal/gpt-cfa
benchmark
Official implementation of TextGym, evaluated language-agent configurations, EXE, and the benchmark experiments.
mail-ecnu/Text-Gym-Agents
Repository for the paper containing the agent_trust experiment code, game prompts, non-repeated and repeated experiment results, environment files, and runnable demos.
camel-ai/agent-trust
Repository containing resources and code for implementing and experimenting with LLMs for vehicle routing problems, including context materials, LLM framework code, oracle algorithms, and verifier code.
Zhehui-Huang/LLM_Routing
benchmark
Repository for RWE-bench, the benchmark and evaluation environment introduced by the paper for testing LLM agents on real-world evidence generation from medical databases.
somewordstoolate/RWE-bench
dataset
Repository containing the FINSABER framework, backtesting code, strategy interfaces, experiment scripts, documentation, and dataset links for reproducing or extending the paper's benchmark.
waylonli/FINSABER
dataset
Official repository containing code, prompts, modules, tests, and post-processing pipeline for generating and evaluating self-generated counterfactual explanations across the paper's datasets and models.
aisoc-lab/llm-sces
implementation
Repository released by the authors for the confidence-elicitation framework and experiments introduced and evaluated in the paper.
MiaoXiong2320/llm-uncertainty
Repository containing EnterpriseBench's application data, task-generation components, enterprise tools, evaluation code, and interactive demonstrations.
ast-fri/EnterpriseBench
Public repository containing the code, method files, data directory, processing notebook, and framework assets used for the paper's MADR experiments.
SangyunLee1027/Code-for-Towards-Faithful-Explainable-Fact-Checking-via-Multi-Agent-Debate
Repository for IllusionReasoning, the paper's real-world visual-illusion benchmark for evaluating LVLM perceptual and reasoning capabilities.
zhaoliangjie55/EMNLP2026_Illusion
dataset
The isbiased library implements the prediction-shortcut reliance diagnostics used to compute relative accuracy drops in the paper.
MIR-MU/isbiased
Repository released by the authors for the study's dataset, source code, and detailed evaluation results.
Wendy-1222/SLM_Jailbreak
dataset
Repository released by the authors for the CAP construction pipeline and verifiable agent-as-a-judge evaluation framework.
WarriorXu0302/CAP-Bench
LangChain repository audited for the default path from model-produced actions to tool execution.
langchain-ai/langchain
LangGraph repository audited for mandatory value authorization before ToolNode invocation.
langchain-ai/langgraph
Reference implementation of the paper's deterministic fail-closed authorization gate, including framework integrations and proof scripts.
raceksd-source/scopegate-runtime
LlamaIndex repository audited for central dispatch, schema validation, and per-call authorization behavior.
run-llama/llama_index
Stripe Agent Toolkit repository audited for client-side authorization of model-supplied payment arguments.
stripe/agent-toolkit
Repository for CAR-bench, including benchmark implementation, tools, task and evaluation workflow, results analysis, and documentation for evaluating multi-turn tool-using LLM agents under uncertainty.
CAR-bench/car-bench
dataset
Official CARE-LoRA implementation built on a repository-local PEFT fork, with reproduction workflows for T5-Base and Mistral-7B-v0.3 experiments, gradient-similarity diagnostics, and comparison baselines.
fishandyu/CARE-LoRA
implementation
Companion implementation for the SD3-Medium DreamBooth personalization experiments reported for CARE-LoRA.
fishandyu/CARE-LoRA-Diffusion
implementation
Open-source LLM adversarial robustness toolkit used by the paper to generate adversarial suffixes for the generator-stage jailbreak experiment.
IntelLabs/LLMart
Repository for the paper's cascaded LLM experiments, including implementation details for the framework evaluated in the paper.
fanconic/cascaded-llms
system
Repository accompanying the paper, containing the P-99 materials, CLAUDE.md instructions, generated problem directories, tests, proof files and the maintained lptp-reference.md.
FredMesnard/LPTP-LLM-P99
BitTern is presented as an open toolkit for low-cost, high-accuracy post-training ternary quantization and 1.58-bit models.
IntelChina-AI/BitTern
implementation
Repository containing the implementation for causal inference via style transfer for OOD generalisation.
nktoan/Causal-Inference-via-Style-Transfer-for-OOD-Generalisation
framework
Official RSS 2023 implementation of Causal MoMa, including Minigrid and iGibson components, causal-inference and data-collection scripts, and policy-training and testing entry points.
JiahengHu/CausalMoMa
Repository containing the open-source LLMCert-B implementation, model-query utilities, experiment code, and materials used for the BOLD bias-detector human evaluation.
uiuc-focal-lab/LLMCert-B
Official repository for the ChAda-ViT architecture, training/evaluation code, and model artifacts.
nicoboou/chadavit
Microsoft repository containing the Python implementation and supporting materials for the plug-and-play CoNLI hallucination detection and reduction framework.
microsoft/CoNLI_hallucination
framework
Official code repository for Chain-of-Models Pre-Training introduced in the paper.
deep-optimization/CoM-PT
Repository for the SVAMP math word-problem benchmark.
arkilpatel/SVAMP
dataset
Repository for the ASDiv diverse math word-problem dataset.
chaochun/nlu-asdiv-dataset
dataset
Repository for the AQuA algebraic word-problem dataset.
deepmind/AQuA
dataset
Repository for BIG-bench, including the Date Understanding and Sports Understanding tasks.
google/BIG-bench
BIG-bench task repository for the StrategyQA question-only evaluation setting.
google/BIG-bench
dataset
Repository associated with the CommonsenseQA benchmark.
jonathanherzig/commonsenseqa
dataset
Repository for the GSM8K grade-school math word-problem benchmark.
openai/grade-school-math
dataset
MIT-licensed Chameleon source repository containing the system implementation, optimization modules, models, benchmark artifacts, and deterministic tests.
RohitSwami33/Chameleon-cybersecurity-ml
benchmark
Repository for the ChannelViT architecture, HCS training/evaluation code, configurations, and pretrained models used to reproduce the paper's experiments.
insitro/ChannelViT
implementation
Repository for the Chat2Workflow benchmark and associated workflow-generation/evaluation resources.
zjunlp/Chat2Workflow
dataset
Public GitHub location for ChatCollab code and data used or produced by the paper.
ChatCollab
dataset
MetaGPT repository, representing a prior meta-programming multi-agent framework compared with ChatCollab.
geekan/MetaGPT
framework
ChatDev repository, representing a prior communicative-agent software-development system compared with ChatCollab.
OpenBMB/ChatDev
framework
Repository for the ChatDev framework and the code/data artifact associated with the paper.
OpenBMB/ChatDev
dataset
Repository explicitly linked by the paper for ChatEDA-Bench, examples of EDA-tool instruction data, API documentation, and the corresponding OpenROAD implementation.
wuhy68/ChatEDAv1
Official implementation and configuration repository for the ChatEval multi-agent referee framework and its evaluation experiments.
chanchimin/ChatEval
Repository containing general and targeted synthetic datasets, generation examples, BERT and GPT-2 adapter notebooks, and evaluators for StereoSet, CrowS-Pairs, and BiasTestGPT.
Pengrui-Han/SyntheticDebiasing
GitHub repository identified by the paper as the location where the dataset can be accessed.
ZihanChen1995/ChatGPT-GNN-StockPredict
dataset
The paper states that the MMF-Trans code has been open sourced at this GitHub URL, with data requiring authorized access. The repository page itself returned 404 during extraction, so its contents could not be inspected.
MMF-Trans
framework
Repository released by the authors for Chronos code and model checkpoints.
amazon-science/chronos-forecasting
implementation
ClawNet repository containing the governed multi-agent social network implementation, including core/gateway, server, desktop, macOS client, and setup components.
hkgai-official/ClawNet
framework
Repository for CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models, including code, configs, data, docs, and README material describing the framework and evaluation setup.
heimy2000/CMAT
dataset
Official code repository for training and testing CMI-MTL on SLAKE, VQA-RAD, and OVQA, including preprocessing scripts and pretrained-model instructions.
BioMedIA-repo/CMI-MTL
Paper-linked repository for the introduced framework.
kilian-group/KBevo
implementation
Official CochlScene repository containing baseline training/evaluation code, dataset metadata, a saved model, and data-preparation scripts.
cochlearai/cochlscene
A GitHub repository listed by the paper as an accompanying curated resource for papers on code as agent harness.
YennNing/Awesome-Code-as-Agent-Harness-Papers
Official Code as Policies directory in the Google Research repository, containing notebooks for LMP examples, HumanEval, RoboCodeGen, code-versus-language reasoning, reactive controllers, and an interactive demo.
google-research/google-research
implementation
Repository containing released benchmark data derived from SWE-CARE, pipeline scripts for filtering, environment building, test generation, agent resolution, and tool evaluation, plus compressed raw experimental outputs.
c-CRAB-Benchmark/dataset
dataset
Repository for the CodeAssistBench benchmark, datasets, prompts, scripts, and evaluation framework for AI coding assistants on real GitHub issues.
amazon-science/CodeAssistBench
dataset
Open-source repository associated with the CodeScout model family and RL recipe for code localization agents.
OpenHands/codescout
system
GitHub repository for CodeTaste, including benchmark infrastructure, agent/evaluation scripts, documentation, and links to benchmark artifacts and precomputed outputs.
logic-star-ai/codetaste
dataset
Repository for Codev-Bench, the developer-centric repository-level code-completion benchmark constructed with Codev-Agent.
LingmaTongyi/Codev-Bench
dataset
Official implementation of CORY, including IMDB training scripts, GSM8K utilities, TRL-based trainers, environment code, and experiment support files.
Harry67Hu/CORY
The latest arXiv v3 links this dedicated repository for the newer CogAgent-9B-20241220 release; it is a direct successor artifact to the paper's CogAgent system.
THUDM/CogAgent
implementation
The paper explicitly states that the CogAgent model and code are available in the CogVLM repository, which contains CogAgent-18B resources alongside CogVLM.
THUDM/CogVLM
implementation
Official implementation of the CogVis framework, including inference, staged adapter training, prompt profiles, and benchmark configuration.
KotlinWang/CogVis
implementation
Repository titled KotiJaddu/Masters-Project, described on GitHub as code supporting the author's Master's thesis, with Python source and model folders.
KotiJaddu/Masters-Project
implementation
Official implementation repository containing the ComfyBench benchmark resources, ComfyAgent code, workflow data, agent modules, inference scripts, and evaluation scripts.
xxyQwQ/ComfyBench
benchmark
Repository containing the evaluator-integrity criteria, scored framework census, citation ledger, conformance and verification tooling, and supporting material used to reproduce or check claims from the paper.
idilgozel/evaluator-integrity
Repository for the LLMWorkflowGenerator project, containing the Python Controller implementation, Android/Termux-oriented workflow automation code, sample files, experiment outputs, and setup instructions.
dos-group/LLMWorkflowGenerator
system
Repository for H2O, the Heavy-Hitter KV-cache eviction method selected as the representative static-sparsification approach.
FMInference/H2O
Official artifact repository for InfiniGen, the recoverable hierarchical KV-cache selection framework evaluated in the paper.
snu-comparch/infinigen
Official repository for vLLM, the GPU-resident memory-management framework used as the full-cache baseline in the study.
vllm-project/vllm
Repository provided by the authors for reproducing the LLM, human-comparison, and algorithmic bandit experiments.
zzy620/LLM-exploration-exploitation
implementation
Official code repository implementing the CompeteAI simulation framework, restaurant environment, agent backends, prompt templates, scenes, database integration, and experiment runner.
microsoft/competeai
Official code repository for the paper, including model runners, interaction-specific evaluation tasks, attention extraction, and attention manipulation scripts for the OmniReason dataset.
DELTA-DoubleWise/OmniReason
Repository for the Bitcoin Fee Rate Prediction Project, including data, model notebooks, scripts, result outputs, plots, and citation information for arXiv:2502.01029.
majiangqin/bitcoin
dataset
PyTorch implementation for Compressed Context Memory, including the compression-memory method introduced and evaluated in the paper.
snu-mllab/context-memory
Repository released by the authors for the compression datasets and the data-collection, processing, and evaluation pipeline used to study the relationship between LLM compression efficiency and downstream capability.
hkust-nlp/llm-compression-intelligence
ScalePlan packages the operator-level analytical cost model, calibration data, memory/MFU prediction, and parallelism search used by MOSAIC.
dmlc/ScalePlan
Repository reported by the paper as the code for confidence estimation in LLM-based dialogue state tracking.
jennycs0830/Confidence_Score_DST
implementation
Official repository and Python package for CONFLARE, supporting document loading, cleaning, chunking, calibration-set creation or loading, and conformal retrieval-augmented generation.
Mayo-Radiology-Informatics-Lab/conflare
framework
Repository linked by the authors as the public code for experiments in Conformal Prediction as Bayesian Quadrature.
jakesnell/conformal-as-bayes-quad
implementation
Repository linked by the paper for CCA/SWE-Bench-related materials.
facebookresearch/cca-swebench
system
Open-source PyTorch repository from which the authors selected reproducible GitHub issues requiring specialist debugging.
pytorch/pytorch
Repository explicitly provided by the authors to reproduce the experiments in the paper.
clinicalml/learn-to-defer
implementation
Companion repository for the paper containing evaluation materials, few-shot and constitutional prompts, and model samples used to document the Constitutional AI experiments.
anthropics/ConstitutionalHarmlessnessPaper
Repository containing the CLL training implementation, weak-signal generation notebook, model utilities, and scripts for synthetic and real-data experiments.
VTCSML/Constrained-Labeling-for-Weakly-Supervised-Learning
Python repository for generating PortBench portfolio-theory tasks and evaluating LLM portfolio decisions.
noahardyx/PortBench
framework
Repository accompanying the paper with selected Python code for feature construction, metrics, and the model. The README states that the full proprietary backtesting and continuous-futures processing framework and licensed data are not included.
joelowj/mtl-tsmom
implementation
Repository released by the authors for constructing hierarchical NAS spaces based on CFGs and reproducing the BOHNAS experiments.
automl/hierarchical_nas_construction
framework
GitHub repository identified by the authors as containing the standard performance forecaster model for the Allora network.
allora-network/allora-forecaster
framework
Repository directory containing the implementation and resources for the CoT-MAE contextual masked auto-encoder introduced and evaluated in the paper.
caskcsg/ir
implementation
Repository containing the paper's data and codebase, including data collection materials for the user feedback and annotation tasks.
lil-lab/qa-from-hf
dataset
Repository containing the automated AI research environments and idea execution trajectories introduced in Chapter 4.
NoviScl/Automated-AI-Researcher
Open-source code, model, and data for the s1 sample-efficient reasoning and budget-forcing work used in Chapters 3 and 4.
simplescaling/s1
Code artifact for the Synthetic Continued Pretraining and EntiGraph experiments in Chapter 2.
ZitongYang/Synthetic_Continued_Pretraining
Python repository containing slow-tail, V-shape, and combined max-cash modules, execution scripts, data-schema documentation, and reproducible output paths for the empirical cash-overlay study.
shaun19920309/gd-cash-overlay-filters
implementation
Repository containing code, data artifacts, and reproducible empirical materials for the continuous smooth-signal growth-versus-defensive allocation framework.
ZheliXiong/continuous-smooth-signals-growth-tech-defensive-income-allocation
implementation
Official implementation of the paper's TinyBabyLM construction, model training, GOOD/BAD contrastive generation, mixed-corpus retraining, benchmark evaluation, bootstrap analysis, and figure/table reproduction.
janulm/CD-for-Synthetic-Data-Generation
Author-linked ConVIRT repository containing the CheXpert 8x200 image-image and text-image retrieval evaluation files; the paper identifies this repository as the public location for its model and collected retrieval datasets.
yuhaozhang/convirt
Repository identified by the paper as the posted model code for reproducing the ConFIRM workflow.
WilliamGazeley/ConFIRM
framework
The open-source repository for the openCHA framework introduced and demonstrated in the paper.
Institute4FutureHealth/CHA
Generation script used in constructing the synthetic natural-language-to-Cypher evaluation data for the NeDRex KG silver-standard benchmark.
lucia990/T2C-synthetic-data-generation
Backend implementation of ChatDRex, including API services, documentation, local setup instructions, and tool-evaluation resources.
SimonSuewerUHH/ChatDRexAPI4J
Frontend implementation for the ChatDRex conversational user interface and interactive biomedical workflow experience.
SimonSuewerUHH/ChatDRexUI
GitHub repository associated with the paper's cooperative knowledge distillation method.
MLivanos/Cooperative-Knowledge-Distillation
framework
Official CooperBench repository containing the benchmark package, dataset tooling, task-running CLI, evaluation logic, and cooperative/solo/team settings for coding-agent experiments.
cooperbench/CooperBench
dataset
Repository containing the implementation and configuration details for LSNPC experiments.
huangweipeng7/lsnpc
implementation
Repository containing datasets, inference-refining code, CoT-UQ uncertainty integration code, configuration, pipeline scripts, and result-analysis utilities.
ZBox1005/CoT-UQ
implementation
Repository released by the authors for the COTCAgent system, including agent modules, temporal-analysis code, knowledge-base files, patient-data examples, tests, and interface components.
FrankDengAI/COTCAgent
implementation
Repository containing the generated synthetic datasets, evaluation outputs, and additional t-SNE visualizations for the paper.
Mohdkhalil/Repository-supplementary-for-LAK-25-paper--Creating-Artificial-Students-that-Never-Existed
Repository for the paper containing CLP/CLSP implementation code, MGSM experiment data, request/merge utilities, and metric scripts.
LightChen233/cross-lingual-prompting
implementation
Repository containing the implementation of CryptoMamba, baseline models, data preprocessing, model training, evaluation metrics, and trading simulation scripts.
MShahabSepehri/CryptoMamba
benchmark
Official CSKV repository with calibration, layer-wise fine-tuning, and inference code for compressed KV-cache models.
wln20/CSKV
RAGQALeaderboard is used as a benchmark environment for evaluating RAG-QA performance across multi-hop, single-hop, and biomedical question-answering tasks.
AQ-MedAI/RagQALeaderboard
dataset
Repository for the CXL-SpecKV memory manager, speculative prefetcher, FPGA cache engine, host library, driver, framework integration, documentation, and tests.
FastLM/CXL-SpecKV
Source-code repository for DAG-MoE, including the learned structural aggregation module evaluated in the paper.
JiaruiFeng/DAG-MoE
system
IBM Agentics is the agentic AI framework on which DAO-AI is built; the paper uses its ATypes, logical transduction, and scalable workflow concepts.
IBM/Agentics
framework
GitHub repository identified by the paper as containing DAO-GP source code and datasets.
anonymous273800/DAO-GP
dataset
Repository for ImageNet-Captions, the dataset introduced to pair ImageNet images with original Flickr text and enable controlled language-image versus classification experiments.
mlfoundations/imagenet-captions
dataset
Repository implementing the Bloom-filter-based Data Portrait method described in the paper.
ruyimarone/data-portraits
implementation
FastChat v0.2.5 question JSONL containing 80 diverse evaluation queries.
lm-sys/FastChat
dataset
Repository implementing data-local, ensemble-based, LLM-guided NAS for multiclass multimodal time-series classification, including local executor scripts, remote LLM proposer scripts, schemas, and a Flask control interface.
emilhar/arl
framework
Contains the code for coarse plan generation, fine-grained plan evolution, SFT-data construction, orchestrator and tool-model inference, distributed corpus curation, prompts, and links to released orchestrator and NP checkpoints.
GAIR-NLP/DataOrchestra
Repository containing the official evaluator, baseline implementations, experimental configurations, and documentation for the DataSpace benchmark.
HKUSTDial/DataSpace
benchmark
Repository cited by the paper for NVIDIA<ef><bf><bd>s Comprehensive Verilog Design Problems benchmark, which provides the selected code-generation and code-comprehension tasks used to evaluate SLMs and LLMs.
NVlabs/verilog-eval
dataset
Repository for the DB2-TransF time-series forecasting model introduced and evaluated in the paper.
SteadySurfdom/DB2-TransF
benchmark
Official repository for the DCQA benchmark, dataset overview, and access instructions.
anranwu-richpo/dcqa
dataset
Microsoft's repository for the DeBERTa implementation, pretrained models, and fine-tuning resources associated with the paper.
microsoft/DeBERTa
implementation
Repository released by the authors for the experiments and data supporting the paper's analysis of probability, memorization, and noisy reasoning in CoT prompting.
aksh555/deciphering_cot
Code repository for the limited teacher supervision decoding method introduced in the paper.
HJ-Ok/DecLimSup
implementation
Repository containing implementations of the tested actor-critic agents and policy parameterizations, experiment configurations, the Backwashing-PID simulator, source plant data, KL utilities, and plotting/reproducibility support.
haseebs/deconstruct-ac
An Awesome-style repository organizing MMR papers, datasets, benchmarks, and related surveys around the paper's PerceptionAlignmentReasoning framework and AnswerProcessExecutable evaluation hierarchy.
formula12/Awesome-Multimodal-Mathematical-Reasoning-Perception-Alignment-Reasoning
AllenNLP contains the official PyTorch ELMo module and scalar-mix implementation for computing the paper's contextual representations.
allenai/allennlp
Official TensorFlow implementation for training the pretrained bidirectional language model and computing ELMo representations introduced by the paper.
allenai/bilm-tf
Repository containing the data-pipeline code, hedging simulator, actor-critic training workflow, saved configurations and models, notebooks, evaluation utilities, tests, figures, and paper materials for reinforcement-learning-based hedging of SPX and SPY exposures.
tlucius16/deep-hedging-rl
framework
Public repository containing software code and datasets or scripts for reproducing the baseline algorithms and experiments.
andrepugni/ESC
benchmark
Repository stated by the paper to contain the market simulation and experiment code.
EduardoGarrido90/micro_agents
implementation
Repository linked by the paper as containing the publicly available datasets and code used for the DRL-in-finance experiments.
Andrei-T-Neagu/DRL_in_Finance
dataset
Repository containing code associated with the paper's A2C, DDPG, PPO, ensemble-selection, and backtesting workflow.
AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020
implementation
Official DeepConf repository implementing offline and online confidence-aware reasoning, voting, trace filtering, warmup thresholding, and early stopping on top of LLM serving backends.
facebookresearch/deepconf
Repository containing source code, datasets, and supplementary materials associated with the multi-horizon NEM electricity price forecasting benchmark.
GaniMosman/Multi-Horizon-EPF-NEM
dataset
The repository contains DeepAries source code, market data folders, checkpoints, model components, experiment code, and instructions for training and inference.
dmis-lab/DeepAries
dataset
Repository for the paper's VRGA method, including Qwen evaluation code, attention-intervention implementation, dataset interfaces, and a reproducible evaluation pipeline.
Ivine11/VRGA
Repository path containing DeepPlanning benchmark code, travel and shopping domain runners, evaluation utilities, configuration files, and instructions for reproducing benchmark results.
QwenLM/Qwen-Agent
dataset
Official repository for DeepSeekMath model checkpoints, evaluation materials, replication resources, and inference examples.
deepseek-ai/DeepSeek-Math
implementation
Official DeepSeek-MoE repository linked by the paper for the introduced architecture and released DeepSeekMoE 16B research artifact.
deepseek-ai/DeepSeek-MoE
implementation
The paper's released DeepSpeed-Chat implementation, including end-to-end RLHF examples, training stages, APIs, inference support, tests, and documentation.
microsoft/DeepSpeedExamples
The DeepSpeed repository contains the framework, code, tutorials, and documentation for large-scale model training and inference, including DeepSpeed-MoE components.
microsoft/DeepSpeed
framework
Repository for DeepTraderX, a deep-learning trading agent running in Threaded-BSE.
armandcismaru/DeepTraderX
framework
Threaded Bristol Stock Exchange repository providing the asynchronous market simulator and working trading agents used for DTX training data and experiments.
MichaelRol/Threaded-Bristol-Stock-Exchange
benchmark
Repository identified by the paper as containing code and data for the finance hallucination experiments.
mk322/fin_hallu
benchmark
Software suite described and used by the paper to calculate reward-representable policy orderings, non-trivial simplifications, and reward functions representing them for specified environments and policy sets.
nikihowe/reward-hacking-paper
Official DeFT research repository containing Triton implementations, tree templates, benchmark scripts, and reproduced performance results for the paper's attention methods.
LINs-lab/DeFT
Code, documentation, and demos for ToolUniverse, the ecosystem for building AI scientists from language models, reasoning models, and agents.
mims-harvard/ToolUniverse
framework
Official implementation repository released for the Demonstrate-Search-Predict framework.
stanfordnlp/dsp
Salesforce AI Research repository for FinDAP: Demystifying Domain-adaptive Post-training for Financial LLMs, including framework materials, training scripts, evaluation guidance, and links to model/data artifacts.
SalesforceAIResearch/FinDAP
dataset
Repository associated with the AgentFail dataset and website for failure lifecycle data and analyses.
Jenna-Ma/JaWs-AgentFail
dataset
Repository containing DPR training, retrieval, evaluation, data-processing tools, configurations, and released model resources.
facebookresearch/DPR
Code repository provided by the paper for DAAM implementations and the IEMOCAP, AG News, CIFAR-100, LoRA-comparison, and appendix experiments.
gioannides/DAAM-PEFT-paper-code
GitHub repository for the TSCC2019 competition data used as real Hangzhou traffic data in the paper's traffic-light-control benchmark.
tianrang-intelligence/TSCC2019
dataset
Repository containing the released loss data and analysis scripts/notebooks for optimal hyperparameter estimation, learning-rate and batch-size scaling, Chinchilla/Skaling fitting, compute-optimal scaling, and uncertainty estimation.
OpenEuroLLM/dense_english_scaling_laws
Official code repository for the DEPS/MC-Planner implementation introduced and evaluated in the paper.
CraftJarvis/MC-Planner
Repository containing the blank Design-OS template, design-case artifacts, prompt files, simulation code, plots, and verification report used to support reuse and replicability testing.
bankh/design-os
framework
GitHub repository for the TalkTuner paper, including code and data for a dashboard that visualizes and controls a chatbot LLM's internal user model.
yc015/TalkTuner-chatbot-llm-dashboard
dataset
GitHub repository for the evolutionary multi-objective neural architecture search approach introduced in the paper.
DevilYangS/EMO-NAS-CD
framework
Repository linked by the paper for reproducing or inspecting the OAS generation experiment.
marques-vinicius/OAGen
implementation
Repository containing code, model files, feature data, and training scripts for the paper's physics-guided bearing prognostic and uncertainty-quantification experiments.
itxwaleedrazzaq/uqpcnn_rul
Repository describing DeXposure-FM as a time-series graph foundation model for forecasting inter-protocol credit exposure, with scripts for experiments, macroprudential tools, checkpoints, and dataset helpers.
EVIEHub/DeXposure-FM
framework
The code URL reported in the paper's v2 HTML/PDF abstract for the DeXposure-FM project.
EVIEHub/graph-dexposure
framework
Official MuJoCo Allegro Hand environments used for the DIME simulation experiments.
NYU-robot-learning/dime_env
Official scripts for collecting and processing demonstrations for the rotation, spinning, and flipping tasks.
NYU-robot-learning/DIME-Demonstrations
Official package for inverse-kinematics-based teleoperation of an Allegro Hand attached to a Kinova Arm.
NYU-robot-learning/DIME-IK-TeleOp
Official implementation repository containing the nearest-neighbor imitation component and links to the other DIME packages.
NYU-robot-learning/DIME-Models
Official code repository for DiaLLM, including supervised fine-tuning, PPO, reward-modeling, evaluation scripts, data folders, and result folders.
WeijieyingRen/DiaLLMs
Code repository for the DiffLOB regime-conditioned diffusion model.
ZhuoHan1998/DiffLOB
implementation
Autonomous-driving decision-making simulator used for DiLu's closed-loop experiments and domain-shift evaluations.
eleurent/highway-env
Code repository for running and visualizing the DiLu closed-loop LLM driving framework.
PJLab-ADG/DiLu
implementation
Official CitySim vehicle-trajectory dataset repository used as the source of one transferred DiLu memory module.
UCF-SST-Lab/UCF-SST-CitySim1-Dataset
Training code for supervised fine-tuning followed by DPO preference learning on causal Hugging Face language models, with dataset and trainer utilities.
eric-mitchell/direct-preference-optimization
implementation
Google Java Format repository; the paper uses Newlines.java from this repository for generated-vs-original unit-test comparison.
google/google-java-format
Junit5 Modular World sample module; the paper uses a Flavor.java code snippet from this repository for prompt-based test generation and comparison.
junit-team/junit5-samples
Contains code, data, configurations, and scripts for the FineLogic training and evaluation experiments.
YujunZhou/FineLogic
benchmark
Author repository for the GSM8K-AI-SubQ reasoning dataset and baselines for distilling LLM decomposition abilities into compact language models.
DT6A/GSM8K-AI-SubQ
dataset
Official source code repository for the Distilling step-by-step method introduced in the paper.
google-research/distilling-step-by-step
implementation
Repository containing code for the supervised and unsupervised LLM uncertainty experiments reported in the paper.
gahdritz/llm_uncertainty
implementation
GitHub repository released by the authors for Distributed Conformal Prediction via Message Passing.
HaifengWen/Distributed-Conformal-Prediction
implementation
Official code repository for the Division-of-Thoughts framework introduced and evaluated in the paper.
tsinghua-fib-lab/DoT
framework
Official repository for DNABERT-2 code, model usage, pre-training/fine-tuning scripts, and GUE benchmark resources.
MAGICS-LAB/DNABERT_2
implementation
Official self-contained SayCan implementation in a simulated tabletop environment using a UR5 setup, ViLD affordances, GPT-3 planning, and a CLIPort pick-and-place policy.
google-research/google-research
implementation
Official SayCan dataset files mapping natural-language user instructions and initial conditions to possible solution plans.
say-can/say-can.github.io
dataset
Repository containing code and notebooks associated with the S&P 500 graph-neural-network forecasting project.
waderylan/sp500-gnn
implementation
The paper-associated repository curates video-LLM systems, visual encoders, datasets, code links, figures, and citation information related to the review.
Darcyddx/Video-LLM
Repository linked by the paper for code and the SelfAware research artifact used to evaluate whether LLMs recognize unanswerable questions.
yinzhangyue/SelfAware
dataset
Repository containing code and data for evaluating uncertainty estimation in LLM instruction-following.
apple/ml-uncertainty-llms-instruction-following
dataset
Repository for Stanford Alpaca, whose Alpaca-7B model is directly evaluated in the paper's altered task-definition experiments.
tatsu-lab/stanford_alpaca
Public source-code repository for the multimodal repair-recognition system introduced and evaluated in the paper.
haanh764/multimodal_repair_recognition
Contains VLN-HAMT and VLN-DUET integrations, training/inference scripts, requirements, and links to R2R-Imagine generations, metadata, extracted features, and trained HAMT-Imagine/DUET-Imagine checkpoints.
akhilperincherry/VLN-Imagine
Repository reported by the paper as containing the prediction model implementation and experiment data.
majuanjuan/Doexpertsperformbetter
dataset
Repository for the DocAgent multi-agent code documentation generation framework introduced by the paper.
facebookresearch/DocAgent
framework
Repository accompanying the paper, linking to hosted C4 data and providing a public discussion venue for documenting additional corpus issues.
allenai/c4-documentation
Repository for the code, human-subject study materials, results, and supplementary materials associated with the Persona framework and AAAI 2025 paper.
YODA-Lab/Persona
framework
Semantic routing package for routing inputs by embedding or intent similarity.
aurelio-labs/semantic-router
package
Framework using repeated generations, verification prompts, and confidence estimates to decide whether to escalate to larger models.
automix-llm/automix
framework
AWS multi-agent orchestration framework that includes prompt-based routing or agent selection patterns.
awslabs/multi-agent-orchestrator
framework
Implementation associated with routing prompts to pre-trained experts after fine-tuned meta-model categorisation.
godcherry/ExpertTokenRouting
implementation
Implementation associated with deciding whether a query requires a complex prompting strategy.
imagination-research/sot
implementation
Iterative multi-agent code generation system using execution success as a routing signal.
JieyuZ2/EcoAssistant
system
LLM routing implementation associated with assessing model adequacy through multiple responses and ground-truth comparison.
kvadityasrivatsa/llm-routing
implementation
Routing-agent implementation using synthetic data and small classifiers for classification-based routing.
lamini-ai/llm-routing-agent
implementation
Orchestrator implementation using decoder-only LLM representations for routing or model selection.
Leeroo-AI/leeroo_orchestrator
system
Framework for serving and evaluating routers that choose between LLMs using preference-oriented routing strategies.
lm-sys/RouteLLM
framework
Task-planning framework in which an LLM selects among models or tools based on descriptions and user tasks.
microsoft/JARVIS
framework
Implementation assessing consistency across reasoning representations for cascade-style routing.
MurongYue/LLM_MoT_cascade
implementation
OpenAI multi-agent orchestration framework discussed as an example of prompt-based routing practice.
openai/swarm
framework
Fine-tuned model framework for API call generation, discussed as treating routing as a code generation problem.
ShishirPatil/gorilla
implementation
Framework for reducing LLM application cost using LLM cascades and related strategies.
stanford-futuredata/Frugalgpt
framework
Adaptive RAG framework that routes among no retrieval, single-step retrieval, and multi-step retrieval paths according to query complexity.
starsuzi/Adaptive-RAG
framework
Code and data for a multi-LLM routing benchmark and evaluation framework.
withmartian/routerbench
dataset
GitHub repository containing the Indonesian financial-domain language-model code and post-trained IndoBERT models.
intanq/indonesian-financial-domain-lm
implementation
Implementations of original, sparse, continuous, and related statistical jump models.
Yizhan-Oliver-Shu/jump-models
framework
Code and model artifacts for Reinforced Token Optimization, the paper's DPO-derived token-reward and PPO/RL alignment method.
zkshan2002/RTO
implementation
Official RSS 2024 repository implementing DrEureka reward generation, reward-aware physics priors, domain-randomization generation, and the forward-locomotion and globe-walking environments.
eureka-research/DrEureka
Provides the Go1 soccer simulation environment, PPO training scripts, pretrained policy evaluation, configuration, and documentation accompanying the paper.
Improbable-AI/dribblebot
Official repository for the paper's LLM-based autonomous-driving demonstrations, including closed-loop HighwayEnv code, scenario assets, and common-sense reasoning materials.
PJLab-ADG/DriveLikeAHuman
Official repository containing the DS-1000 data, execution-based evaluators, environment files, inference scripts, and released baseline results.
xlang-ai/DS-1000
dataset
Repository for evaluating LLMs on the DSBC dataset, including response generation, LLM-as-judge evaluation, command-line usage, and dataset evaluation utilities.
traversaal-ai/DSBC-Data-Science-Task-Evaluation
dataset
Repository for DSPy, the programming model and compiler introduced by the paper.
stanfordnlp/dspy
framework
Code repository for the DSTCGCN traffic forecasting model introduced and evaluated in the paper.
water-wbq/DSTCGCN
implementation
Official D-DiT repository with environment setup, pretrained 512-base and supervised-fine-tuned checkpoints, inference examples, data formats, training configurations, and distributed training commands.
zijieli-Jlee/Dual-Diffusion
system
A scikit-learn-style implementation of a collection of statistical jump models, including the model family used to identify asset-specific market regimes.
Yizhan-Oliver-Shu/jump-models
package
Repository indicated by the paper as the code website for DVGNN.
gorgen2020/DVGNN
implementation
Repository containing experimental analysis, tools, and code associated with dynamic design of machine-learning pipelines via metalearning.
ealcobaca/dynamic-design-machine-learning-pipelines
framework
The first author's repository providing implementations of statistical jump models, including methods relevant to the sparse jump-model analysis used in the paper.
Yizhan-Oliver-Shu/jump-models
package
Official GitHub repository containing code for the paper Dynamic Graph Convolutional Network with Attention Fusion for Traffic Flow Prediction.
trainingl/AFDGCN
implementation
Repository for the Dynamic Meta-Learning for Adaptive XGBoost-Neural Ensembles implementation, including source code and test datasets as described by the paper.
aasedek/Adaptive-XGBoost-Neural-Network-Ensemble
framework
Repository containing data and code for the ICLR 2023 PromptPG paper, including the TabMWP dataset and implementations/evaluation scripts for GPT-3, UnifiedQA, TAPEX, and PromptPG experiments.
lupantech/PromptPG
dataset
Python repository containing pseudo-answer generation, silver-label construction, input processing, multi-task training, inference, and evaluation scripts for the six reported datasets.
XieZilongAI/E2E-AFG
framework
Repository containing the EasyRAG pipeline, ingestion code, retrievers, rerankers, prompt templates, challenge scripts, Docker deployment, FastAPI service, Streamlit WebUI, and processed challenge assets.
BUAADreamer/EasyRAG
dataset
The EasyTool directory in Microsoft JARVIS contains implementation code, requirements, generated tool-instruction data for ToolBench and RestBench, FuncQA data, and commands for reproducing the reported evaluations.
microsoft/JARVIS
implementation
Official Microsoft Research implementation of the Sui Generis scoring pipeline introduced in the paper.
microsoft/SuiGeneris
Public GitHub repository for the study's replication materials, mirrored in Zenodo.
codescene-research/echoes-of-ai-emse-2025
dataset
Official code repository for the EconAgent paper, including simulation scripts, configuration, data, and AI-Economist foundation components.
tsinghua-fib-lab/ACL24-EconAgent
Repository containing the EDA augmentation implementation and code associated with the paper's experiments.
jasonwei20/eda_nlp
Code repository linked by the paper for the ChatSim system and its introduced simulation pipeline.
yifanlu0227/ChatSim
implementation
Code repository for CAID, including the multi-agent workflow where a central manager delegates tasks to engineer agents that run asynchronously in isolated git worktrees, plus scripts and task modules for Commit0 and PaperBench experiments.
JiayiGeng/CAID
system
NovGrid extends MiniGrid with a generalized novelty generator so environment properties and dynamics can change and agents can be evaluated on adaptation to those changes.
eilab-gt/NovGrid
dataset
OWL is compared against Efficient Agents in the agent framework evaluation.
camel-ai/owl
framework
Smolagents is compared against Efficient Agents and OWL in the agent framework evaluation.
huggingface/smolagents
framework
Repository linked by the paper as its code resource, associated with the OAgents/Efficient Agents work.
OPPO-PersonalAI/OAgents
framework
Public code repository for the DASH architecture-search algorithm introduced and evaluated in the paper.
sjunhongshen/DASH
framework
Official repository for the NAACL 2021 paper, containing data and model resources needed to reproduce reported results.
luyang-huang96/LongDocSum
implementation
fairseq example code and resources for training and evaluating the paper's MoE language models.
pytorch/fairseq
implementation
Source-code repository for Helium, the workflow-aware LLM serving system proposed and evaluated in the paper.
mlsys-io/helium_demo
framework
Public source repository for vLLM, the LLM serving system introduced and evaluated in the paper.
vllm-project/vllm
The paper's vLLM fork and branch containing its Activated LoRA serving and cross-model prefix-cache reuse implementation.
tdoublep/vllm
implementation
Maintained companion repository for the survey's literature organization and updates on efficient multimodal large language models.
lijiannuist/Efficient-Multimodal-LLMs-Survey
Repository for the Temporal Neural Common Neighbor model introduced in the paper.
GraphPKU/TNCN
implementation
Repository containing SDPG agents, configurations, Genesis environments, models, training/evaluation scripts, baseline dependencies, and Go2 hardware-related files.
HaoxiangYou/SDPG
Official repository for ActPRM, containing the active-PRM package, training and ProcessBench evaluation scripts, examples, and links to released models and data.
sail-sg/ActivePRM
Official experiment code for the paper's expert-wise mixed-precision MoE quantization method.
nowazrabbani/moe_quantization
Repository released by the authors for PTA-IRT code and data.
DeepSoftwareAnalytics/PTA-IRT
Repository associated with EfficientLLM for the benchmark codebase, metric API, evaluation workflows, and planned model artifacts.
DLYuanGod/EfficientLLM
Repository containing the code, experiment configurations, and model artifacts for the structured state-space work discussed in the paper.
HazyResearch/state-spaces
Official code repository for generating embeddings and pseudo-labels, collecting training dynamics, computing importance scores, selecting ELFS coresets, and training CIFAR and ImageNet classifiers.
eltsai/elfs
Official repository containing scripts and links to reconstruct the ELI5 dataset, build support documents and splits, format multi-task data, train and evaluate the reported models, and use the released pretrained checkpoint.
facebookresearch/ELI5
dataset
Repository implementing the paper's ELSAA hybrid attention mechanism, including sortLSH sparse attention, RACE low-rank attention, denominator-aware fusion, causal variants, and experiment scripts.
mahdiheidari721/ELSAA
Repository for EmbedLLM materials, described by the paper as containing the dataset, code, and embedder for further research and application.
richardzhuang0412/EmbedLLM
dataset
Official repository for EMMA, containing the LAVIS-based ALFWorld finetuning setup, links to released training artifacts, and trajectory/experiment logs for EMMA and the Reflexion LLM teacher.
stevenyangyj/Emma-Alfworld
Repository for the Embodied Web Agents project, including web environment hosting instructions and model-running folders for indoor, outdoor, and geolocation tasks.
Embodied-Web-Agent/Embodied-Web-Agent
system
Python SDK that lets users obtain drone observations and issue control actions through the Embodied City online API.
tsinghua-fib-lab/embodied-city-python-sdk
package
Repository containing simulator-related materials, datasets, task code, prompts, VLN code, and documentation for the EmbodiedCity benchmark.
tsinghua-fib-lab/EmbodiedCity
dataset
Official code repository for the EMERGE framework, including data processing, retrieval, fusion, training, and evaluation components.
yhzhu99/EMERGE
Code and experiment resources for measuring how context-characteristic sensitivity changes across instruction-fine-tuning stages.
copenlu/context-characteristics-sensitivity
implementation
Repository named Emoji-Embedding-For-Finance, cited throughout the paper as the source for model-vs-BERT comparisons, emoji frequencies, BTC/VCRIX figures, sentiment time series, and trading-strategy outputs.
QuantLet/Emoji-Embedding-For-Finance
implementation
Repository linked as 'Code' from the paper's official project page; its README states that it maintains an overview/implementation of the Habitat-MAS benchmark and EMOS multi-agent system and contains a habitat-mas component plus instructions for running the EMOS demo.
SgtVincent/EMOS
benchmark
Official repository for the paper, containing code and data artifacts for generating analysis-report features and training the hybrid asset pricing model.
chengjunyan1/AAPM
implementation
Core open-source Academy implementation for building and deploying stateful actors and autonomous agents across distributed and federated research infrastructure.
academy-agents/academy
Code for generating and scoring multiple-choice questions from scientific papers, used as the implementation basis for the paper's information-extraction case study.
auroraGPT-ANL/MCQ-and-SFT-code
Repository released by the authors for ILM code, data, trained models, and human-evaluation outputs/responses.
chrisdonahue/ilm
implementation
Official code and data repository for the ALCE benchmark and evaluation framework introduced in the paper.
princeton-nlp/ALCE
dataset
Pre-release Python/PyTorch code for building chart-image datasets, splitting data, training the ResNet trader, and inferring triple-I weights.
ZhuZhouFan/TWMA
implementation
Repository for implementing Iter-CoT, the paper's iterative bootstrapping method for chain-of-thought prompting.
GasolSun36/Iter-CoT
implementation
Preferred Multi-turn Benchmark for Finance in Japanese, used by the paper to evaluate generation quality across financial dialogue tasks.
pfnet-research/pfmt-bench-fin-ja
benchmark
Pathway is used as the vector store implementation in the paper's retrieval system.
pathwaycom/pathway
implementation
Stated repository for the modular Python prototype implementing the neuro-symbolic ontology-based LLM validation pipeline.
ruslanmv/Neuro-symbolic-interaction
system
Repository containing implementation for the PSX interpretability algorithms and models discussed in the paper.
sahar-arshad/PSX-Interpretability
implementation
Repository indicated by the paper as containing code for AdvDistill; the URL returned 404 when fetched during extraction.
shreyansh-2003/AdvDistill
implementation
Official CASE inference-code repository linked directly by the paper. The repository implements the context-aware semantic embedding pipeline with a scikit-learn-style transformer interface.
SAP-samples/case
implementation
Public implementation of the structured-matrix Transformer enhancement framework introduced in the paper.
newbeezzc/MonarchAttn
framework
Code repository for the Focus reference-free uncertainty-based hallucination detector.
zthang/focus
Official PyTorch implementation of JADE and distribution point for the text portion of the CC3M-QA-DC dataset.
CASIA-IVA-Lab/OPT_Questioner
Official repository for the paper containing scripts for question-driven caption generation, GPT-3.5 answer generation, preprocessing and evaluation, plus released captions and prediction files.
ovguyo/captions-in-VQA
Repository containing the LoT prompting implementation, scripts for CoT and LoT experiments, requirements, and quick-run instructions.
xf-zhao/LoT
framework
Gym-PushT is the simulation environment used for ENPIRE's heuristic-learning autoresearch comparison and is explicitly cloned for the Push-T setup.
huggingface/gym-pusht
GitHub repository cited by the paper as the source of the second obesity classification dataset.
pymche/Machine-Learning-Obesity-Classification
dataset
Repository reported by the paper as containing code, curated data pointers, generated figures, and result tables for the reproduction and robustness analysis.
ZheliXiong/Ensemble-RL-through-Classifier-Models
implementation
Official repository containing the code used to train and evaluate the ME-DST models introduced in the paper.
WRF32-10/ME-DST
Implementation of faithfulness-aware decoding used for the advanced-decoding baseline.
amazon-science/faithful-summarization-generation
implementation
FactPEGASUS code and models used to test whether the proposed augmentation transfers to another factuality-aware contrastive pipeline.
meetdavidwan/factpegasus
implementation
Official CLIFF implementation used as the contrastive-learning baseline and as the training framework combined with the proposed counterfactual augmentation.
ShuyangCao/cliff_summ
implementation
Official ERA repository containing the EPL training code, online RL framework, environment setup, evaluation integration, and links to the curated prior datasets.
Embodied-Reasoning-Agent/Embodied-Reasoning-Agent
Repository hosting the ESG-FTSE corpus of news articles with ESG relevance labels.
mariavpavlova/ESG-FTSE-Corpus
dataset
Repository released by the authors containing code for the agentic benchmark assessment and related experiments.
uiuc-kang-lab/agentic-benchmarks
benchmark
Repository associated with the paper's contamination-detection work for LLM evaluation. The paper links it as code and data; the currently visible README describes a lightweight tool for identifying and analysing potential contamination without access to LLM training data.
liyucheng09/Contamination_Detector
dataset
Repository URL listed by the paper for the implementation of the confidence IQN experiments.
YHL04/confidenceiqn
implementation
Repository containing the paper's data-processing, rephrasing, fine-tuning, detector-evaluation, and post-processing code for reproducing the reported experiments.
eth-sri/malicious-contamination
A production-grade evaluation toolkit for LLM agent outputs, including metrics for diversity, reliability, cascade uncertainty, perturbation consistency, consistency, factual grounding, hallucination, explainability, and drift.
mukund1985/llm-eval-toolkit
framework
Repository containing the AGENTbench harness used to evaluate coding agents under NONE, LLM, and HUMAN repository-level context settings on AGENTbench and SWE-bench Lite.
eth-sri/agentbench
benchmark
Repository associated with the CogEval cognitive-map study containing conversation artifacts, task templates, and a conversation visualizer.
cogeval/cogmaps
Public GitHub repository released by the authors to support reproducibility and further research on financial relationship graph evaluation.
FreddieNIU/Financial-Graph-Evaluation
dataset
Repository containing the HumanEval hand-written programming benchmark and code for evaluating generated solutions.
openai/human-eval
dataset
Repository described as a resource hub for understanding, detecting, and mitigating biases in financial-domain LLMs, including a Structural Validity Checklist, a literature review dashboard, and an automatic bias detection dashboard.
Eleanorkong/Awesome-Financial-LLM-Bias-Mitigation
framework
Official repository containing data-download scripts, annotation tools, data-construction code, API and open-source model inference code, evaluation code, and reward-model evaluation utilities.
LesterGong/MMRB
Repository containing the code released for the ClinMM-Bench study.
ruiyang-medinfo/ClinMM
Repository associated with the M4 competition dataset and methods, used by the paper for benchmark data and base learner forecasts.
Mcompetitions/M4-methods
dataset
Repository containing the source code for the paper's FFORMA and ES-RNN ensemble experiments.
Pieter-Cawood/FFORMA-ESRNN
benchmark
Repository for LogiEval, the paper's prompt-style logical-reasoning benchmark suite for evaluating large language models.
csitfun/LogiEval
benchmark
LogiQA 2.0 repository referenced for the benchmark and for the newly constructed 2022-onward out-of-distribution logical-reasoning data.
csitfun/LogiQA2.0
dataset
Official repository containing the LoCoMo data release, conversation-generation code, prompts, and evaluation scripts.
snap-research/LoCoMo
dataset
Phoenix is cited among tools that provide analytics and evaluation orchestration capabilities for agent or LLM evaluation.
Arize-ai/phoenix
DeepEval is listed among tools that support analytics, evaluation orchestration, and debugging for LLM or agent evaluation workflows.
confident-ai/deepeval
OpenAI Evals is discussed as an open-source framework for specifying evaluation tasks and metrics and automating execution and reporting.
openai/evals
HAL is cited as a holistic agent leaderboard or harness for centralized and reproducible agent evaluation.
princeton-pli/hal-harness
benchmark
Inspect AI is cited as a framework for large language model evaluations and included among evaluation tooling examples.
UKGovernmentBEIS/inspect_ai
Repository named in the paper for ICD coding explainability evaluation resources, including RD-IV-10-related artifacts and generated rationales.
mingyangligithub/ICD-Coding-Explainability-Evaluation
dataset
Paper-provided implementation link for the evaluation-awareness scaling-law experiments; the arXiv HTML resolves through an Anonymous Github mirror.
eval-awareness-scaling-laws
benchmark
Official repository for the survey, containing the paper's benchmark reference framework, figures, and benchmark bibliography.
YHPeter/Awesome-RAG-Evaluation
Repository containing the EviReform source code, configuration, prompt assets, released evaluation data, index artifacts, metric/statistics code, and reproduction instructions.
XrazyMee/EviReform
R code, datasets, and experiment scripts for EvoAAA, the evolutionary autoencoder architecture search methodology introduced in the paper.
fcharte/EvoAAA
dataset
Repository containing code and technical details for the Multi-Agent Scoring System for essay assessment.
AzizovDilshod/Multi-agent-System-for-Essay-Assessment
system
OpenAI's released distributed implementation of the evolution-strategies algorithm studied in the paper.
openai/evolution-strategies-starter
Repository providing BanditBench and inference code; the paper also notes installation via pip install banditbench.
allenanie/EVOLvE
package
Official repository for the CodeAct framework, evaluation code, CodeActAgent deployment components, scripts, and links to the released data and models.
xingyaoww/code-act
implementation
Repository identified by the paper as containing the code and data for the software-developing agent framework evaluated in the study.
OpenBMB/ChatDev
dataset
The repository is linked by the paper as the location for data and code and contains files including a notebook, UNSW-NB15 dataset archive, and feature metadata.
pcwhy/XML-IntrusionDetection
dataset
Repository named by the authors as containing all code for the experiments that apply feature importance, SHAP, and LIME to PPO portfolio-management predictions.
aleedelarica/XDRL-for-finance
implementation
Existing Reinforcement learning in portfolio management repository that the authors identify as the starting framework for integrating explainability into a PPO-based model.
deepcrypto/Reinforcement-learning-in-portfolio-management-
framework
The cpath package implements the paper's counterfactual-path method for R and Python.
pievos101/cpath
package
UnifiedSKG is the structured knowledge grounding model used in the paper's text-to-SQL case study.
HKUNLP/UnifiedSKG
system
Official implementation of Pattern-Exploiting Training and iterative PET introduced in the paper.
timoschick/pet
implementation
Repository for the x-stance multilingual stance-detection dataset evaluated by the paper.
ZurichNLP/xstance
dataset
Repository containing the benchmark data, task files, representative logs, and evaluation scripts for AutoGen, MetaGPT, and TaskWeaver.
lurf21/Agent_Evaluation_Framework
dataset
Repository for the MachineSoM experiments, including sampled evaluation data, prompts, agent-society simulation code, agent-count/round/strategy ablations, ANOVA evaluation, and conformity/consensus plotting utilities.
zjunlp/MachineSoM
Implements SimCLR-style HAR training and evaluation on MotionSense, including preprocessing, transformations, model definitions, utilities, and a demonstration notebook.
iantangc/ContrastiveLearningHAR
GPT-Engineer is listed as a code-domain LLM-based single-agent system and cited as a GitHub project that generates code repositories from prompts.
AntonOsika/gpt-engineer
system
GPTresearcher is listed as a research-domain LLM-based autonomous agent for online comprehensive research.
assafelovic/gpt-researcher
system
AIlegion is listed as a universal LLM-powered autonomous agent platform.
eumemic/ai-legion
implementation
LoopGPT is listed as a universal modular Auto-GPT-style LLM agent framework.
farizrahman4u/loopgpt
framework
AGiXT is listed as a universal AI automation platform with instruction management, memory, and plugins.
Josh-XT/AGiXT
LangChain is discussed as an open-source framework supporting LLM-based agent software development and tool integration.
langchain-ai/langchain
framework
DemoGPT is listed as a code-support LLM-based agent system for creating LangChain applications through prompts.
melih-unsal/DemoGPT
system
AgentGPT is discussed as an agent framework offering browser-based assembly, configuration, deployment, fine-tuning, and local data incorporation.
reworkd/AgentGPT
framework
Auto-GPT is discussed as an open-source agent template/framework for decomposing objectives and executing tasks in a loop.
Significant-Gravitas/Auto-GPT
framework
SmolModels / smol-ai developer is listed as a code-domain LLM-based agent system with self-feedback and tool use.
smol-ai/developer
system
WorkGPT is discussed as an open-source GPT agent framework for invoking APIs.
team-openpm/workgpt
framework
SuperAGI is listed as a universal open-source autonomous AI agent framework.
TransformerOptimus/SuperAGI
framework
XLang is discussed as an open-source framework for building and evaluating language model agents through executable language grounding.
xlang-ai/xlang
framework
BabyAGI is listed as an LLM-based agent that creates tasks from objectives and stores or retrieves task results.
yoheinakajima/babyagi
system
Repository for the CogMir framework's core data assets and high-level experimental prompt-design logic, including datasets corresponding to Appendix C and prompt templates corresponding to Section 4 and Appendix D.
XuanL17/CogMir
BabyAGI is described as an OpenAI-powered task management system that uses vector databases such as Chroma or Weaviate to manage, prioritize, execute, store, and recall task-related information.
yoheinakajima/babyagi
framework
Code for defining text-to-text tasks and mixtures, preprocessing and evaluating datasets, training and fine-tuning T5 models, and reproducing the paper's experiments, with links to released checkpoints.
google-research/text-to-text-transfer-transformer
Repository for ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook, including experiment code, datasets, scripts, and setup instructions.
forangel2014/ExpNote
dataset
Repository containing the 50-claim development dataset, the 25-claim post-finalization dataset, and dataset statistics used in the paper.
LaraHack/linkflows_claims_dataset
Repository containing materials from Stages 1, 2, and 3 of the expert formalization study evaluating the super-pattern.
LaraHack/linkflows_formalization_study
Repository containing the paper's released Self-Contrast code and data.
THUDM/Self-Contrast
implementation
Open-source implementation of the paper's GPT-2 generation, candidate ranking, and training-data memorization attack workflow.
ftramer/LM_Memorization
Repository containing FactReview, RefCopilot, demos, source code, scripts, tests, and documentation for evidence-grounded reviews of ML papers.
DEFENSE-SEU/FactReview
framework
Repository containing pilot and main JSON datasets, prompt generation code, evaluation code, prompt templates, and unit-group definitions for the FAITH paper.
ZHANG-MENGAO/FAITH
dataset
Author-linked PyTorch codebase for the paper's transformer self-supervision experiments, including SynCo-style synthetic negatives, DeiT/Swin configurations, pretraining, and linear evaluation.
giakoumoglou/synco-v2
PyTorch code, configurations, training and unmasking scripts, evaluation utilities, and pretrained checkpoints for ImageNet 256x256 and 512x512 MaskDiT models.
Anima-Lab/MaskDiT
implementation
Code implementing the Favi-Score introduced and evaluated in the paper.
vodezhaw/faviscore
Code repository linked by the paper for the FedSPM method and experiments.
zijianwang0510/FedSPM
Official repository for reproducing the paper's output-refinement and policy-refinement experiments.
aypan17/llm-feedback
Repository explicitly published with the paper for the FEVER annotation interfaces; the current repository also contains dataset preparation, scoring, and baseline components.
awslabs/fever
Repository explicitly published with the paper for the FEVER baseline pipeline implementing evidence retrieval and textual entailment.
sheffieldnlp/fever-baselines
Repository associated with the Cross-Attentive Time-Series Trend Network described and evaluated in the paper.
kieranjwood/x-trend
framework
Official repository for the paper, containing code for synthetic hallucination generation, reward-model training and evaluation, sample hallucination data, and links to released data.
du-nlp-lab/FG-PRM
Open-source repository associated with PIXIU and FinBen, containing financial LLM resources, evaluation datasets, benchmark materials, code, and links to related models and leaderboards.
The-FinAI/PIXIU
dataset
Repository implementing FinBERT and providing training, prediction, and model resources associated with the paper.
ProsusAI/finBERT
Repository indicated by the authors for the FinBERT2 work, including the specialized encoder and related downstream variants or resources.
ValueSimplex/FinBERT2
system
ProgramFC repository used as the implementation basis for the LLM-based composite fact-checking system in the experiment.
teacherpeterpan/ProgramFC
system
Repository for FAVOR with model files, inference code, environment specification, example data, and checkpoint setup instructions.
BriansIDP/AudioVisualLLM
Official repository providing the paper's Fine-Grained RLHF implementation, QA-FEEDBACK data, reward-model training code, RLHF scripts, trained-model references, and annotation interfaces.
allenai/FineGrainedRLHF
Repository containing preprocessing, model-definition, training, testing, and performance-analysis code for mapping CSU veterinary medical summaries to SNOMED-CT diagnosis codes.
adam-kiehl/DiagnosisCoding
Official repository for offline reward-model training and preference-based language-model fine-tuning, including smaller fine-tuned models and a subset of collected human labels.
openai/lm-human-preferences
Official repository implementing the paper's RL4VLM training pipeline, GymCards environment, modified LLaVA components, and PPO training for GymCards and ALFWorld.
RL4VLM/RL4VLM
GitHub repository for a Chinese financial news sentiment classification dataset containing train and test CSV files and financial news sentiment labels.
wwwxmu/Dataset-of-financial-news-sentiment-classification
dataset
Repository path containing the AdvBench harmful-behaviors data from which the paper uses a 50-prompt subset across 32 categories.
llm-attacks/llm-attacks
Repository containing code for FinEAS and the paper's BERT, BiLSTM, and FinBERT financial-news sentiment experiments, together with reported result tables.
lhf-labs/finance-news-analysis-bert
benchmark
Repository containing data preprocessing code, FineFT algorithm training/validation/testing scripts, VAE routing components, trading-environment implementation, baseline code, and analysis utilities.
qinmoelei/FineFT_code_space
framework
Google Research Big Vision repository containing the UViM codebase used for the paper's depth, panoptic-segmentation, and colorization evaluations.
google-research/big_vision
Official Google Research directory containing the FSQ paper README and reference FSQ Colab/code artifact.
google-research/google-research
Official MaskGIT JAX implementation used as the basis for the paper's MaskGIT FSQ-versus-VQ experiments.
google-research/maskgit
Python source code repository for FINMEM, the LLM trading agent with layered memory and character design.
pipiku915/FinMem-LLM-StockTrading
system
Repository for the FinReport code and datasets released by the paper.
frinkleko/FinReport
dataset
Astock dataset used for stock and news data, train-validation-test splitting, OOD analysis, and backtesting.
JinanZou/Astock
dataset
Repository for the paper's dataset construction pipeline, data collection module, FinRpt framework modules, benchmark evaluation code, fine-tuning setup, reinforcement-learning setup, and website front-end code.
jinsong8/FinRpt
dataset
GitHub repository associated with the paper's benchmark for online financial RAG evaluation.
PhealenWang/financial_rag_benchmark
dataset
Repository released by the authors for FinTexTS framework code and pilot study implementation.
leejaehoon2016/FinTexTS
dataset
Open-source implementation repository for FinWorld, the end-to-end financial AI research and deployment platform introduced in the paper.
DVampire/FinWorld
framework
Contains FireAct prompts, task and tool definitions, trajectory-generation and evaluation code, fine-tuning scripts, example training data, and model references.
anchen1011/FireAct
implementation
Open-source implementation of FlashAttention referenced by the paper.
HazyResearch/flash-attention
implementation
Source code and experiment resources for the Fleet of Agents framework introduced and evaluated in the paper.
au-clan/FoA
Repository containing the Flow multi-agent workflow automation implementation, including workflow management code, prompts, validators, notebooks, and generated examples.
tmllab/2025_ICLR_FLOW
framework
Code repository for the FlowAgent framework introduced by the paper.
Lightblues/FlowAgent
framework
Official repository containing FlowBench source data organization, turn-level and session-level evaluation code, scripts, prompts, and setup instructions.
Justherozen/FlowBench
dataset
GitHub Gist with a replenishment plan generated by the Flowr DC Replenishment Planning Agent, including outlet allocations, route assignments, vehicle assignments, route summary, consolidation opportunities, and human review queue.
https:/
GitHub Gist with a purchase-order report generated by the Flowr Procurement and Ordering Agent, including order quantities, supplier justifications, delivery estimates, consolidated supplier orders, and human review flags.
https:/
Repository listed by the paper for code associated with dataset analysis, object-detection benchmarking, and cost-aware sequence active-learning experiments.
olivesgatech/FOCAL
dataset
Repository made available by the authors for the proposed models used to forecast extreme Bitcoin volatility movements.
dorienh/bitcoin_synthesizer
implementation
Repository for the FiGASR package and related sentiment-indicator resources.
lucabarbaglia/FiGASR
package
Repository containing Python code for fine-grained aspect-based sentiment analysis in the economic news setting.
sergioconsoli/SentiBigNomics
implementation
Public multivariate time-series dataset repository containing the exchange-rate data used as real-data-E.
laiguokun/multivariate-time-series-data
dataset
Lag-Llama pretrained model repository used as the probabilistic zero-shot forecaster in the experiments.
time-series-foundation-models/Lag-Llama
implementation
Official implementation of the Diffusion Model-Based Predictor baseline for robust offline RL against state-observation perturbations.
zhyang2226/DMBP
implementation
Repository containing the implementation and results for LSTM and GRU time-series forecasting experiments discussed by the paper.
Alebuenoaz/LSTM-and-GRU-Time-Series-Forecasting
implementation
Repository containing FoT code, task and benchmark scripts, datasets, model and method modules, and evaluation instructions for Game of 24, GSM8K, MATH-500, and AIME.
iamhankai/Forest-of-Thought
framework
Repository containing more detailed prompts and implementation code for the LAWN antenna self-evolution framework discussed in the paper.
ChangyuanZhao/LAE_evolving
framework
Repository stated by the authors to contain the complete source code employed in the research.
Suhasnadh/Power-Consuption
implementation
Official code for the paper, including the local Qwen3-4B/BGE-M3 RAG pipeline, controlled diagnostic experiment, BEIR evaluation, cross-encoder comparison, and gating analyses.
Silk-Road/causal-rag-rerank
Repository for the paper 'From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents', containing implementation-related folders such as agents, configs, envs, plan generation, prompts, tasks, utilities, and experiment scripts.
import-myself/AHP
framework
Repository for the paper From Emergence to Control: Probing and Modulating Self-Reflection in Language Models, describing probing vectors, model insertion, and reflection analysis for controlling self-reflection in LLMs.
xzAscC/ProbingReflection
implementation
Repository for ALARM, including the front-end GUI, back-end algorithms, and the anomaly/feature-importance simulation code described by the authors.
xyvivian/ALARM
A maintained paper list and resource collection about LLM-as-a-judge.
llm-as-a-judge/Awesome-LLM-as-a-judge
Repository for the paper's semi-automated ontology and knowledge-graph construction pipeline, including prompts, code, data, generated artifacts, results, and evaluation materials.
fusion-jena/automatic-KG-creation-with-LLM
Repository containing the reproducibility-related publication data and analysis code from the authors' prior biodiversity deep-learning study, which supplied the source dataset for the current pipeline.
fusion-jena/Reproduce-DLmethods-Biodiv
Repository accompanying the review, containing the detailed thematic scoring by co-authors, supplementary review material, and diagrams.
mak-raiaan/LLMAgentsReview
Repository titled for the paper 'From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications' and identified by GitHub as the code repository for the paper.
jiangfeibo/ComAgent
framework
BeeAI is described as the experimental platform central to IBM's ACP, supporting local-first orchestration, agent discovery, REST endpoints, SDKs, telemetry, and multi-agent execution.
i-am-bee/beeai-framework
framework
The MCP servers repository is cited as an ecosystem of reference and integration servers for file management, databases, Google Drive, Git, GitHub, GitLab, Slack, Google Maps, image generators, and search APIs.
modelcontextprotocol/servers
implementation
OpenAI Swarm is reviewed as a lightweight, stateless abstraction for multi-agent systems with agent definitions, dynamic handoffs, context management, direct function calling, streaming, and backend flexibility.
openai/swarm
framework
Open-source Microsoft GraphRAG repository implementing the graph-based indexing and retrieval/summarization approach described in the paper.
microsoft/graphrag
implementation
Repository reported by the paper as containing code and data for the proposed news-aware LLM time series forecasting framework.
ameliawong1996/From_News_to_Forecast
dataset
Open-source OpenCode repository corresponding to one of the agentic tools evaluated by the paper.
anomalyco/opencode
Open-source Kilo Code repository corresponding to the agentic coding tool selected for the paper's second prototype.
Kilo-Org/kilocode
Repository containing code and data for the HippoRAG family, including the framework introduced and evaluated in this paper.
OSU-NLP-Group/HippoRAG
framework
Repository path for a Workflow Composer that transforms natural-language research questions into executable HyperFlow workflows for the 1000 Genomes Project, including source code, tests, Skills/resources, CLI commands, and evaluation-related materials.
hyperflow-wms/1000genome-workflow
dataset
A companion GitHub repository associated with the survey on agentic workflow optimization.
IBM/awesome-agentic-workflow-optimization
Repository for the paper containing raw experimental data, reasoning processes and outputs, keyword-statistic results, LLM-as-a-judge scores, and score-analysis spreadsheets.
ChangWenhan/FromThinking2Output
dataset
Official companion repository for the tutorial, containing the paper materials and a resource browser organized around its world-model and world-action-model taxonomy.
clearlab-sustech/WorldModelSurvey
Repository associated with the paper<ef><bf><bd>s recursors/refiners work, containing generated Prolog programs, models, execution traces, and related materials for the implemented system.
ptarau/recursors
framework
AWorld-RL is the linked project repository that houses FunReason-MT materials and describes the introduced multi-turn function-calling data-synthesis framework.
inclusionAI/AWorld-RL
framework
The FunReason v1 paper explicitly directs readers to this GitHub repository for code and dataset; the URL currently redirects to the renamed BalanceSFT repository.
BingguangHao/FunReason
dataset
Repository identified by the paper as containing the pre-processed dataset, raw news article data, and implementation code for M2VN.
Yoontae6719/M2VN-Multi-Modal-Learning-Network-for-Volatility-Forecasting
dataset
Repository containing GAAMA's typed memory graph, semantic and PPR retrieval components, prompts, storage adapters, and LoCoMo evaluation scripts.
swarna-kpaul/gaama
framework
Repository containing retrieval, gain-signal synthesis, selector training, and evaluation code for GainRAG.
liunian-Jay/GainRAG
Repository for the Game-theoretic LLM paper, including source code, setup instructions, complete-information game experiments, workflow experiments, and Deal-or-No-Deal experiments.
Wenyueh/game_theory
benchmark
Official GameplayQA benchmark codebase containing data-processing, model-evaluation, judging, ablation, evaluation, and plotting workflows.
HATS-ICT/GameplayQA
benchmark
Web-based tool developed for synchronized single- and multi-video timeline annotation and verification used in constructing GameplayQA.
wangyz1999/sync-video-label
Gapetron is the modular large-scale pretraining toolkit used to train the Gaperon model suite and released as a primary implementation artifact of the paper.
NathanGodey/gapetron
Repository reported by the author as containing the code and dataset used in the paper.
bvsdinda/TPE-LSTM
dataset
Official implementation and evaluation code for GEAR, including generation benchmarks and a CUDA-supported GEAR-KIVI implementation.
opengear-project/GEAR
Repository containing the code used to construct and evaluate nearest-neighbor language models, including datastore building and FAISS-backed retrieval.
urvashik/knnlm
implementation
ytopt is a machine-learning-based autotuning and hyperparameter-optimization framework used in Section IV-B to search coefficient spaces for the reviewed scaling laws.
ytopt-team/ytopt
package
The Lila benchmark repository supplies the program-form mathematical reasoning data used in the paper's mathematical program-synthesis experiments.
allenai/Lila
dataset
Official AASbyLLM research repository containing the prototype implementation, simplified source code, AAS samples, prompts, raw evaluation results, evaluation spreadsheet, figures, and demos associated with the paper.
YuchenXia/AASbyLLM
Repository released by the authors for the GAR method, including code and retrieval results.
morningmoni/GAR
Public repository for the paper's generative-agent architecture and Smallville simulation code.
joonspk-research/generative_agents
Repository linked directly by the paper; it provides the satellite-domain dataset/knowledge material and a simple notebook example for validating the generative AI agent.
RickyZang/GAI-agent-satellite
dataset
Official repository for the ToxiGen synthetic toxic/benign text dataset evaluated as an alternative and complementary augmentation source.
microsoft/ToxiGen
dataset
PyTorch repository containing generative sparse-index-tracking code, comparison code, a GECCO 2023 directory, backtesting material, and instructions for obtaining the associated dataset.
kayuksel/generative-opt
implementation
Code for training WSGAN with a StyleGAN2-ADA base architecture on weakly supervised CIFAR10 and LSUN datasets.
benbo/stylewsgan
Code for jointly training the DCGAN-based WSGAN and label model, together with weak-label files and instructions for the principal datasets.
benbo/WSGAN-paper
Public repository from which the authors select 96 model-specific jailbreak prompts used as the jailbreak query group.
elder-plinius/L1B3RT4S
Official code repository for GRT, including task configurations, VLM-based keypoint preparation, population-based deformation search, simulator evaluators, and analysis scripts.
RCHI-Lab/GRT
Repository explicitly linked by the paper for GestureGPT prompts and corresponding data samples used to guide the three-agent architecture.
studyzx/GestureGPT_ISS
Official source repository for the Gibson Environment, including installation, assets integration, rendering, agent examples, and training demos.
StanfordVL/GibsonEnv
dataset
Official repository containing Gorilla inference resources, APIBench data, evaluation scripts, model outputs, and materials for reproducing the paper's results.
ShishirPatil/gorilla
OpenAI Evals, the framework the report states it is open-sourcing for creating and running model benchmarks and inspecting performance sample by sample.
openai/evals
Repository for the SeeAct generalist web agent, including code, data links, and evaluation tools associated with the paper.
OSU-NLP-Group/SeeAct
Repository containing code and instructions for preparing nuScenes-derived prompts, fine-tuning GPT-3.5, generating motion-planning outputs, and evaluating the GPT-Driver approach.
PointsCoder/GPT-Driver
implementation
Public prompts and code for the GPT-based automated review generation workflow used in the study.
zrobertson466920/GPT_Auto_Review
implementation
Author-owned repository containing ROG experiment code, FedAvg attack scripts, compression configurations, model components, and minimal example data.
KAI-YUE/rog
Repository linked by the paper as the implementation of Grammar Search for multi-agent systems.
mayanks43/grammar_search
framework
Repository providing the authors' implementation of a Graph Attention Network layer and an execution example.
PetarV-/GAT
implementation
Code and sample artifacts for concept-specific KG generation, UMLS subgraph sampling, node and edge clustering, personalized KG composition, BAT model training, prediction, and baseline execution.
pat-jj/GraphCare
implementation
Source code for GraphGPT and the Graph Eulerian Transformer workflow.
alibaba/graph-gpt
framework
RAGChecker is an open-source visual analytics tool that compares LLM outputs against source documents, supports GraphEval+ and SICI-style detection, and presents claim reliability through an interactive quadrant-based visualization.
tanmayagrawal21/RAGChecker
framework
Open R1 provides the GRPO/SFT training framework that the study extends and is also the source of the no-reflection comparison used in the reflection-reward ablation discussion.
huggingface/open-r1
Repository supplied by the author for the paper's GRPO-with-reflection implementation, training workflow, evaluation code, and reported experimental results.
Red-Scarff/GRPO_reflection
implementation
Repository accompanying the paper with GSM-Symbolic templates and generated benchmark data, including GSM-Symbolic, GSM-Symbolic-P1, and GSM-Symbolic-P2 resources.
apple/ml-gsm-symbolic
dataset
Repository for the GTA benchmark, dataset, code, and evaluation materials for general tool agents.
open-compass/GTA
dataset
Repository for the GUARD-SLM method, including activation extraction and analysis code, activation classification, inference and judging scripts, datasets, and experimental results.
solidlabnetwork/GUARD-SLM
Official GuardAgent code repository containing the guard agent implementation, prompts, callable tools, and runner scripts.
guardagent/code
implementation
Official repository for the EICU-AC and Mind2Web-SC benchmark resources introduced by the paper.
guardagent/dataset
dataset
Official repository for H3M-SSMoEs containing Python code, model components, training and backtesting scripts, and links to datasets and model weights.
PeilinTime/H3M-SSMoEs
dataset
Repository explicitly linked by the paper for the HaGRID dataset, downsampled/trial versions, pretrained models, and dynamic gesture recognition demo.
hukenovs/hagrid
dataset
Official repository for the HalluLens benchmark, including materials for the extrinsic hallucination evaluation tasks and associated evaluation workflow.
facebookresearch/HalluLens
The FacTool repository contains a dedicated Halu-J directory and the resources released for the critique-based hallucination judge and ME-FEVER.
GAIR-NLP/factool
Official open-source implementation and data repository for HarmBench, including benchmark data, red-teaming baselines, evaluation classifiers, pipeline scripts, and adversarial-training code.
centerforaisafety/HarmBench
benchmark
Repository stated as the release location for HDFlow code and data.
wenlinyao/HDFlow
dataset
Documentation and examples for obtaining embeddings from the HeAR health-acoustic foundation model through its research API.
Google-Health/google-health
Repository directory containing CT Foundation API documentation, demos, and resources for generating embeddings from CT volumes.
Google-Health/imaging-research
Repository associated with the paper's released LOFin benchmark and HiREC implementation.
deep-over/LOFin-bench-HiREC
dataset
Official repository linked by the paper for HippoRAG code and data.
OSU-NLP-Group/HippoRAG
Hosts the paper project page, benchmark overview, examples, statistics, comparison graphics, and model leaderboard for HLV-1K.
Vincent-ZHQ/HLV-1K
dataset
Open-source implementation of the HAL evaluation harness introduced and evaluated in the paper.
princeton-pli/hal-harness
Open-source HomeRobot codebase containing shared agents and interfaces, Habitat-based simulation support, hardware control for the Stretch robot, and OVMM baseline implementations.
facebookresearch/home-robot
Repository containing code to reproduce the HCNN experiments reported in the paper.
FinancialComputingUCL/HomologicalCNN
benchmark
PyTorch implementation of the Hopfield, HopfieldPooling, and related continuous modern Hopfield-layer functionality introduced and evaluated in the paper.
ml-jku/hopfield-layers
Repository containing the baseline model code and pipeline for HotpotQA data download, preprocessing, training, prediction, and evaluation.
hotpotqa/hotpot
Repository containing annotated transcripts of each participant made available for future studies.
safety-research/how-ai-impacts-skill-formation
dataset
TheAgentCompany repository contains sandboxed work environments, task directories, evaluators, task instructions, and supporting files for many task instances listed in the paper's appendix task table.
TheAgentCompany/TheAgentCompany
dataset
Repository for coding-agent token-consumption analysis, including dataset-building scripts, multi-model analysis scripts, phase-level token decomposition, and self-prediction correlation computation.
LongjuBai/agent_token_consumption_analysis
implementation
Python codebase for running the ensemble generalization-gap experiments, computing dataset complexity metrics, and generating per-dataset outputs and figures.
zubair0831/ensemble-generalization-gap
benchmark
Open-Instruct repository released with the paper to support reproduction and further research on open instruction tuning, including T"ULU-related artifacts.
allenai/open-instruct
GitHub directory linked by the paper for the deterministic prediction task source code, including Pauli string multiplication, divide-and-conquer, letter replacement, and addition-related files.
EdenCodeInc/PyCliffordMCP
benchmark
Repository containing the dataset and experimental code for the study of memory addition, deletion, and experience-following behaviour in LLM agents.
yuplin2333/agent_memory_manage
dataset
Repository containing the prototype implementation for customizing and probing leaderboards with the paper's evaluation approach.
swarooprm/Leaderboard-Customization
The repository provides code folders for HAG-XAI object detection, HAG-XAI image classification, FullGradCAM for Yolo-v5s, and FullGradCAM for Faster-RCNN, along with links to experimental materials, human attention data, and pretrained model files.
GitVirTer/HAG-XAI
framework
Repository linked directly from the paper; it contains the implementation notebook, Appendix.pdf, Focus data, and transformed MLC data.
ruijiang81/hai-blbf
implementation
Repository containing data and analysis code for the human-alignment AI-assisted decision-making study.
Networks-Learning/human-alignment-study
dataset
Contains the Auto_Driving_Highway code, prompt materials, results, and instructions for training an RL agent with an LLM in the reward loop.
JingYue2000/In-context_Learning_for_Automated_Driving
framework
Azure Verified Modules is used by the paper as a cloud-native curated module ecosystem that demonstrates governance, standards, testing, versioning, and consistent interfaces.
Azure/Azure-Verified-Modules
framework
Repository indicated by the paper for prompts, code, anonymised data, and the full questionnaire related to the AI Narrative Test.
Mosh0110/AI-narrative-test
benchmark
Repository for the S&P 500 membership forecasting project, including EDA.ipynb, Modeling_Process.ipynb, model-interpretability figures, and Python dependencies.
VidhiAgrawal/sp500_finance
implementation
Source code for the HybRank hybrid and collaborative passage-reranking model.
zmzhang2000/HybRank
implementation
Repository linked by the paper as the code for the HyGRL framework.
wjywjy123/HyGRL
implementation
Repository containing the HypeLoRA MLP and Transformer hyper-networks, dynamic LoRA layers, RoBERTa builders, GLUE data loading, calibration metrics, experiment configurations, and experiment-running utilities.
btrojan-official/HypeLoRA
implementation
Official implementation repository for HyperAgent, including the multi-agent software engineering framework and benchmark reproduction scripts.
FSoft-AI4Code/HyperAgent
framework
GitHub repository for the ICICLE method introduced and evaluated in the paper.
gmum/ICICLE
framework
Repository containing ToolEmu code, emulators, evaluators, curated toolkit and test-case assets, scripts, and notebooks.
ryoungj/ToolEmu
benchmark
Repository for the IDQL method introduced in the paper, including offline-training and fine-tuning scripts and the diffusion/IQL learner implementation.
philippe-eecs/IDQL
implementation
Author-released implementation of PromptInject, the modular framework used to assemble prompts and evaluate LLM robustness to adversarial prompt attacks.
agencyenterprise/PromptInject
GitHub repository released by the authors for IL-PCSR and developed models.
Exploration-Lab/IL-PCSR
dataset
Repository containing data preparation, BERT-based and T5 training and evaluation scripts, late-fusion evaluation, and experiment configurations for the paper's CBM models.
salanueva/CBM
Repository containing the ImageRAG codebase, configurations, scripts, evaluation workflow, and pointers to released data, caches, and checkpoints.
om-ai-lab/ImageRAG
implementation
Complete codebase and setup instructions for the sentiment-driven stock prediction experiments.
Walids35/capstone-stock-prediction
implementation
Repository maintained by the authors as an official page and living resource list for the survey on implicit reasoning in LLMs.
digailab/awesome-llm-implicit-reasoning
Official HarmBench repository used to generate adversarial safety-evaluation test cases for the downstream RLHF experiment.
centerforaisafety/HarmBench
Open-source repository cited as the source for the Reuters & Bloomberg news-title stock-prediction dataset used to build headline vectors.
WenchenLi/news-title-stock-prediction-pytorch
dataset
Repository titled Anote-Text-Classification containing dataset folders, trial runs, requirements, README explanations, and model performance comparisons for GPT-3.5 Turbo, SetFit, and BERT across the evaluated datasets.
iiWhiteii/Anote-Text-Classification
implementation
Repository for the CARE native retrieval-augmented reasoning framework, including scripts, evaluation resources, documentation, and training examples.
FoundationAgents/CARE
framework
Official FactCC implementation and model used to score whether generated summary claims are factually consistent with source documents.
salesforce/factCC
implementation
Preliminary implementation of the paper's multiagent debate experiments, with code for arithmetic, GSM8K, biography, and MMLU tasks.
composable-models/llm_multiagent_debate
Repository for Fusion-in-Decoder, providing the Natural Questions version augmented with DPR-retrieved passages that RETRO uses for its question-answering experiment and representing a principal comparison system.
facebookresearch/FiD
NexusRaven-V2 repository linked by the paper for the Nexus function-calling evaluation benchmark.
nexusflowai/NexusRaven-V2
benchmark
Repository containing notebooks for SFT and LoRA-based DPO training, generation and reward-model evaluation of the four OPT-350M variants, evaluation data and JSON outputs, plots, and examples of noisy preference pairs.
PiyushWithPant/Improving-LLM-Safety-and-Helpfulness-using-SFT-and-DPO
dataset
Code repository for the paper's QE-based machine-translation feedback-training experiments and RAFT+ method.
zwhe99/FeedbackMT
implementation
Code repository for the Synchronously Self-Reviewing fine-tuning method introduced and evaluated in the paper.
liangyupu/SSR
Repository for the Unsupervised Passage Re-ranking method introduced in the paper, including the codebase and paper-linked data/checkpoints.
DevSinghSachan/unsupervised-passage-reranking
Code repository for the MAP paper, including implementations and evaluation scripts for Tower of Hanoi, CogEval graph tasks, PlanBench, StrategyQA, and transfer experiments.
MAPLLM/MAPICLR2025sub
system
Microchain is the agent-based library used to inject function declarations, descriptions, and examples into prompts, call functions during the reasoning loop, and record assistant/user chat-completion chains.
galatolofederico/microchain
framework
S-LoRA is the scalable multi-adapter serving baseline whose unified pool does not retain history KV caches in the evaluated configuration.
S-LoRA/S-LoRA
vLLM is the serving engine extended by FastLibra and a principal baseline with static LoRA/KV cache partitioning and LRU management.
vllm-project/vllm
Repository containing code and standardized data for direct experiments, indirect matched-content experiments, the AllSides news-choice case study, and the Amazon seller-choice case study; it also documents the inference environment and points to hosted aggregated outputs.
aflah02/LLM-Latent-Source-Preferences
dataset
Public repository for InlineCoder, the framework introduced and evaluated in the paper.
ythere-y/InlineCoder
dataset
Repository containing the MMT-VQA Fairseq-based implementation, training and evaluation scripts, dataset preparation instructions, and access information for Multi30K-VQA.
libeineu/MMT-VQA
Official repository listed by the paper for the InfiR model family and associated model resources.
Reallm-Labs/InfiR
implementation
Repository linked by the paper for InfoMosaic-Bench/InfoMosaic-Flow resources.
DorothyDUUU/Info-Mosaic
dataset
Published ETT dataset collected by the authors and used as a core benchmark dataset in the paper.
zhouhaoyi/ETDataset
dataset
Source code for the Informer model and experiments.
zhouhaoyi/Informer2020
framework
Aider source repository analyzed for user-driven loop design, repo-map retrieval, edit formats, and summarization behavior.
Aider-AI/aider
implementation
OpenCode source repository analyzed for tool interface design, event bus, SQLite session persistence, dynamic tools, and role-based sub-agents.
anomalyco/opencode
implementation
Moatless Tools source repository analyzed for MCTS orchestration, tree-structured state, action classes, semantic search, in-memory shadow mode, and actor-critic routing.
aorwall/moatless-tools
implementation
AutoCodeRover source repository analyzed for phased scaffold control, search-only tools, AST-aware retrieval, SBFL, and Docker-based execution.
AutoCodeRoverSG/auto-code-rover
implementation
Cline source repository analyzed for recursive control flow, IDE coupling, shadow git checkpoints, delegation, and LLM-initiated compaction.
cline/cline
implementation
Prometheus source repository analyzed for LangGraph-based phased control, graph-scoped state, knowledge graph retrieval, per-node tool scoping, and multi-tier persistence.
EuniAI/Prometheus
implementation
Gemini CLI source repository analyzed as one of the 13 coding agent scaffolds.
google-gemini/gemini-cli
implementation
Codex CLI source repository analyzed for event-driven ReAct control, dynamic tool rebuilding, sandboxing, Guardian safety routing, memory extraction, and sub-agent delegation.
openai/codex
implementation
Agentless source repository analyzed for fixed-pipeline architecture, hierarchical localization, sampling, and JSONL pipeline state.
OpenAutoCoder/Agentless
implementation
OpenHands source repository analyzed for event-sourced architecture, tool interfaces, Docker execution, and delegation mechanisms.
OpenHands/OpenHands
implementation
mini-swe-agent source repository analyzed as a deliberately minimal baseline scaffold with a single bash tool and simple ReAct loop.
SWE-agent/mini-swe-agent
implementation
SWE-agent source repository analyzed for ReAct control loop, tool bundles, retry behavior, Docker isolation, and compaction processors.
SWE-agent/SWE-agent
implementation
DARS-Agent source repository analyzed for depth-first tree search, SWE-agent-derived tools, greedy LLM critic selection, and Docker reset/replay state recovery.
vaibhavagg303/DARS-Agent
implementation
A topic-agnostic, provenance-first pipeline for legitimate AI-assisted drafting of a Related Work section using human-authored structured notes, strict no-invention constraints, interaction logs, generated taxonomy, draft output, audit table, provenance card, and related artifacts.
RutaBinkyte/AI-RO
framework
Repository associated with the paper's survey of instruction-tuning research.
xiaoya-li/Instruction-Tuning-Survey
Python repository associated with hybrid physics-based and data-driven building energy modeling, with folders for evaluation, feature generation, forecasting, models, preprocessing, and utilities.
Leo-VK/hybrid_bem
dataset
Official DVLR repository containing training, MathVerse evaluation, example, and environment files for the proposed decoupled visual interpretation and linguistic reasoning framework.
guozix/DVLR
implementation
Repository containing code notebooks, data files, tickers, metrics/metadata, SQL queries, and the list of companies associated with the paper's algorithmic stock-market trading system.
JuanCarlosKing/StockmarketAlgoritmicTrading
dataset
Repository for the MiniGrid gridworld environment used for the paper's four-room and six-room navigation experiments.
maximecb/gym-minigrid
benchmark
Repository for the FastAPI control server, callback-augmented interactive trainer, React/TypeScript dashboard, examples, and LLM-based tuning demonstration.
yuntian-group/interactive-training
framework
The paper states that the ICM protocol is open source under the MIT license and that referenced workspaces are available or buildable through this repository.
RinDig/Interpretable-Context-Methodology-ICM-
framework
Repository identified by the paper as containing the code for the GDELT headline extraction, FinBERT sentiment scoring, feature engineering, modeling, and backtesting workflow.
yukepenn/macro-news-sentiment-trading
implementation
Public code repository for the paper's context-faithfulness experiments.
liyp0095/ContextFaithful
benchmark
Repository for InvestLM, the LLaMA-based financial-domain instruction-tuned model released to the research community under the same licensing terms as LLaMA.
AbaciNLP/InvestLM
implementation
Python project for forecasting variance-covariance matrices in a Markowitz framework across cryptocurrency and traditional asset markets; the repository README states that it produced the paper's results.
Maciej-13/vcov_forecast
framework
Repository for IPO Finance Agent containing benchmark code, data directories, rubric artifacts, model-result files, and domain/workflow analysis outputs.
benstaf/ipoagent
benchmark
Repository containing the IQ-Learn implementation and usage materials for the paper's algorithm.
Div99/IQ-Learn
Repository for the IRPAPERS benchmark introduced by the paper.
weaviate/IRPAPERS
dataset
Experimental code used for the retrieval and question-answering evaluations reported in the paper.
weaviate/query-agent-benchmarking
Official Python repository accompanying the paper, organized into pretraining and fine-tuning code.
avinashsai/MML
Open-source baseline compliance assessment agent for the CISO persona.
IBM/itbench-ciso-caa-agent
Repository containing the sample ITBench scenarios released for community familiarization and development.
IBM/itbench-sample-scenarios
Open-source baseline SRE agent introduced and evaluated with ITBench.
IBM/itbench-sre-agent
Code and data repository for reproducing the paper's evaluator training, SFT+ILR, SFT+DPO, naive-ILR, and supervision-quality experiments.
helloelwin/iterative-label-refinement
dataset
Repository for JailbreakEval, an integrated toolkit containing multiple mainstream safety evaluators and supporting voting-based judgments of jailbreak success.
ThuCCSLab/JailbreakEval
Repository storing submitted jailbreak prompts, responses, classifications, and metadata for attacks and defenses tracked by JailbreakBench.
JailbreakBench/artifacts
Official JailbreakBench codebase implementing dataset access, model querying, jailbreak and refusal judges, red-teaming evaluation, defenses, logging, and submission workflows.
JailbreakBench/jailbreakbench
benchmark
Repository containing Stage 1 JEPA+DAAM training, Stage 2 decoder training, FSQ and mixed-radix packing, a HiFi-GAN decoder with optional DAAM gating, and DeepSpeed integration.
gioannides/Density-Adaptive-JEPA
system
Repository associated with the Jr. AI Scientist system; the paper points readers there for issues, comments, questions, and planned codebase release.
Agent4Science-UTokyo/Jr.AI-Scientist
system
FastChat's LLM-judge artifact containing the MT-bench evaluation machinery, judge prompts, and released benchmark/preference resources associated with the paper.
lm-sys/FastChat
benchmark
Official K-COMP codebase with retrieval, data-processing, training, inference scripts, environment configuration, short medical descriptions, and links to model checkpoints and datasets.
jeonghun3572/K-COMP
framework
Facebook/FAIR Memory Networks repository containing a KVmemnn directory with the Key-Value Memory Network model and scripts for building, training, evaluating, and interactively inspecting WikiMovies memory data.
facebook/MemNN
implementation
Repository path containing code or supplementary material for the shell-based keyword-search agent used in the paper.
amazon-science/aws-research-science
system
Repository for KG-Reasoner containing KG retrieval, GNN ranking, backtracking, RL training, reward server, evaluation scripts, and training/test data directories.
Wangshuaiia/KG-Reasoner
Official implementation of the KnowAgent framework, including HotpotQA and ALFWorld path-generation scripts, trajectory filtering and merging, and LoRA-based knowledgeable self-learning.
zjunlp/KnowAgent
Repository containing the question-generation compression workflow, paper-card generation, syntactic multihop experiments, datasets, evaluation scripts, and reported result files.
anvix9/llama2-chat
system
Official repository released with the paper, containing extensible implementations of KTO, DPO, offline PPO, ORPO, and other human-aware loss functions.
ContextualAI/HALOs
implementation
Repository for the technical report, providing code for high-frequency trading prediction under label imbalance, including MLP, LSTM, BERT, and Mamba backbones plus class weighting and data balancing options. The original dataset is not provided because of copyright restrictions.
RS2002/Label-Unbalance-in-High-Frequency-Trading
framework
Demonstration repository for the paper, including environment setup, dataset preparation, unsupervised detector execution, TS2Vec representation training, and feature preprocessing.
imTurkey/Label-Efficient-Interactive-Time-Series-Anomaly-Detection
implementation
Repository for the KPI anomaly-detection dataset used as one of LEIAD's three benchmark datasets.
NetManAIOps/KPI-Anomaly-Detection
benchmark
Official LaMMA-P repository containing code, PDDL resources, scripts, Fast Downward submodule setup, and MAT-THOR test dataset files for running the method in AI2-THOR.
tasl-lab/LaMMA-P
dataset
Open-source GPTSwarm implementation for building graph-based LLM agents and composite swarms, with modules for graph execution, LLM backends, memory, environments, and agent optimization.
metauto-ai/gptswarm
Repository linked by the paper for code and data supporting Uncertainty Quantification with Attention Chain.
Yinghao-Li/UQAC
Official repository accompanying the GPT-3 paper, containing synthetic arithmetic and word-scrambling datasets, dataset statistics, 175B samples, a model card, and benchmark-overlap examples.
openai/gpt-3
Repository for PRONTOQA containing data-generation and analysis code plus released model outputs; the paper states that these artifacts reproduce its analysis and figures.
asaparov/prontoqa
The repository contains an mgsm directory with TSV files for the ten translated languages plus English and manually translated few-shot exemplars.
google-research/url-nlp
dataset
Official demonstration code implementing the paper's language-model planning and admissible-action grounding workflow.
huangwl18/language-planner
PIXIU provides FinMA models, FLARE financial evaluation benchmark tasks, and instruction data used as a baseline or source in the paper.
chancefocus/PIXIU
benchmark
Curated collection of papers associated with the survey's coverage of LLM-agent research.
luo-junyu/Awesome-Agent-Papers
Open-source CAMEL framework for autonomous cooperation among communicative agents using inception prompting and role-play.
camel-ai/camel
framework
Open-source multi-agent collaborative framework associated with MetaGPT, discussed as a representative framework that embeds human workflow processes and SOPs into language-agent collaboration.
geekan/MetaGPT
framework
Open-source AutoGen framework for creating LLM applications using customizable agents that can be programmed through natural language and code.
microsoft/autogen
framework
Author-maintained repository for tracking LLM-based multi-agent papers and organizing them into streams such as frameworks, orchestration and efficiency, problem solving, world simulation, datasets, and benchmarks.
taichengguo/LLM_MultiAgents_Survey_Papers
A GitHub repository made public by the authors to curate papers related to LLM safety.
tjunlp-lab/Awesome-LLM-Safety-Papers
Repository containing the paper list associated with the survey on LLM-based agents for software engineering.
FudanSELab/Agent4SE-Paper-List
dataset
Official repository containing the paper's human-agent collaboration datasets, training/testing code for HotpotQA, StrategyQA, and InterCode, processed training data, and original evaluation outputs.
XueyangFeng/ReHAC
dataset
Repository containing the mathematical problem dataset, evaluation code, and model results associated with the paper.
jboye12/llm-probs
dataset
Repository containing the data and code for the LLM biased reinforcement learning experiments.
william-hayes/LLMs-biased-RL
dataset
The repository contains task implementations for the Iowa Gambling Task, Cambridge Gambling Task, and Wisconsin Card Sort Test, LLM integration utilities, oTree interface components, run scripts, configuration files, and links to analytical code and data.
ynulihao/LLM_vs_Human_Decision_Making
benchmark
Official code repository for the Rememberer agent and Reinforcement Learning with Experience Memory experiments.
OpenDFM/Rememberer
Repository released by the authors for reproducing the Zero-shot-CoT experiments.
kojima-takeshi188/zero_shot_cot
Google DeepMind repository containing code for prompt optimization, prompt evaluation, linear regression, and traveling-salesman experiments described in the paper.
google-deepmind/opro
Repository for TraceLLM, the LLM-based synthetic microservice trace generator and related experimental code.
ldos-project/TraceLLM
system
Official source-code repository for the ICPI algorithm and experiments introduced in the paper.
ethanabrooks/icpi
Repository for the paper's LLM-based anomaly detection implementation, including data-processing scripts, raw data archive, demo scripts for SFT, transfer learning, LoRA, online detection, catastrophic forgetting, and ICL.
PoSeiDon-Workflows/LLM_AD
implementation
A GitHub repository linked by the authors as a resource for recent work on LLMs for ML workflows.
t-harden/LLM4AutoML
The repository contains the paper's source code in a Jupyter notebook and the RAG knowledge-base text used for the demonstration.
explainable-digital-twins/RAG-DDDAS
system
Repository for transformer and foundation models for financial time-series forecasting, including data folders, model implementations, scripts, result files, notebooks, and reproduction instructions.
UVA-MLSys/Financial-Time-Series
dataset
Fin-LLAMA: efficient fine-tuning of quantized LLMs for finance.
Bavest/fin-llama
implementation
Cornucopia-LLaMA-Fin-Chinese: Chinese finance-oriented LLaMA model referenced by the survey.
jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese
implementation
Repository containing the entity-linking pipeline, relevant-document counting code, and data used for the paper's analysis.
nkandpa2/long_tail_knowledge
Repository linked by the paper for released code; it contains Product-Key Memory Layer support and a PKM-layer notebook.
facebookresearch/XLM
An up-to-date resource list for large multimodal agents associated with the survey paper.
jun0wanan/awesome-large-multimodal-agents
Repository implementing the GANPO latent adversarial regularization framework introduced by the paper.
enyijiang/GANPO
implementation
Source-code repository for the TACO-RL algorithm, configurations, training pipeline, and CALVIN-based experiments introduced in the paper.
ErickRosete/tacorl
Microsoft UniLM's LayoutLMv3 implementation, fine-tuning examples, and links to pre-trained and task-fine-tuned models.
microsoft/unilm
implementation
Repository backing the paper's companion website and editable table of reviewed studies, access modes, reproducibility attributes, comparison practices, and leaked datasets.
leak-llm/leak-llm.github.io
The official code repository for experiments and evaluation associated with the Leaky Thoughts paper.
parameterlab/leaky_thoughts
benchmark
Repository containing the annotation backend, web frontend, model API, example notebooks, and explanation-supported training components for named entity recognition, relation extraction, and sentiment analysis.
INK-USC/LEAN-LIFE
Repository linked by the paper as the available code for the conformal abstention and uncertainty-evaluation work.
sinatayebati/vlm-uncertainty
benchmark
Official implementation and experiments for Graph Neural Controlled Differential Equations.
WonderSeven/graph-neural-cdes
framework
Repository described as the official codebase for the ACL submission titled 'Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization'.
gb-kgp/VocabReplace-Then-Expand
implementation
Contains data resources and code for the two-stage training procedure, inference, and evaluation of fine-grained attributed generation.
LuckyyySTA/Fine-grained-Attribution
dataset
Repository for reproducing the FAIR paper, including scripts for inferring student mistakes, collecting teacher responses, training distilled student models, and testing accuracy.
zhuochunli/Learn-from-Committee
framework
Repository containing synthetic-data preparation, GRPO and SFT training code, experiment recipes, model evaluation scripts, and configurations used to reproduce the synthetic-to-real reasoning experiments.
kilian-group/phantom-reasoning
Official implementation of the paper's TraceCodegen training framework, including preprocessing, execution, buffer-based self-sampling, training configurations, and inference.
microsoft/TraceCodegen
Official implementation and pipeline repository for representation learning in time-domain high-energy astrophysics, including event-file representations, feature extraction, dimensionality reduction, clustering, datasets, encoders, and demonstration notebook.
StevenDillmann/ml-xraytransients-mnras
implementation
Repository titled 'BERTOps: Learning Representations on Logs for AIOps' containing data, results, source code, annotated datasets, dataset distributions, and scripts for preparing a pretrained ITOps-domain model.
BertOps/bertops
dataset
Official accompanying code repository for DemPref, including experiment code, raw simulation data, and Jupyter notebooks used to reproduce figures.
malayandi/DemPrefCode
Code accompanying the paper's limited-expert-prediction learning-to-defer experiments.
ptrckhmmr/learning-to-defer-with-limited-expert-predictions
implementation
Repository containing code and data for the FILCO project, including context scoring, dataset preparation, model training, inference, and evaluation scripts.
zorazrw/filco
implementation
Official implementation of ProverGen, the framework that generates ProverQA, which is the primary benchmark used for PRoSFI training and evaluation.
opendatalab/ProverGen
benchmark
Repository containing code for the paper's Robot Language Model approach to grounded task planning.
dnandha/RobLM
system
Repository released by the authors for Learning to Self-Verify Makes Language Models Better Reasoners.
chenyuxin1999/Learning-to-Self-Verify
Contains code for the supervised baseline, trained reward model, PPO fine-tuned policy, model card, and links to the released human-feedback and evaluation data.
openai/summarize-from-feedback
dataset
Official implementation and pretrained model weights for the CLIP method introduced and evaluated in the paper.
OpenAI/CLIP
implementation
Official repository for LeetCodeDataset, containing versioned data, data-processing code, and the eval_lcd evaluation toolkit.
newfacade/LeetCodeDataset
dataset
Repository explicitly linked by the paper for the open-sourced Lemur models and implementation resources.
OpenLemur/Lemur
Repository for the ICML 2026 paper; it is the designated implementation and results release target for the benchmark.
CEA-LIST/less-precise-more-reliable-vlms
Repository accompanying the paper with PRM800K labels, labeler instructions, grading logic, MATH train/test splits, and scored evaluation samples.
openai/prm800k
Official experiment code for training LEVER verifiers, executing generated programs, and reproducing the paper's language-to-code evaluations.
niansong1996/lever
CAIL2019 is used as an additional legal case similarity setting involving civil cases such as private lending, IP disputes, and maritime law.
alumik/cail2019
dataset
Repository associated with the paper's rationale-augmented dialogue understanding experiments and released resources.
ShoRit/RATDIAL
dataset
Code, model-training scripts, refined UMLS relation data, architecture assets, and setup instructions for the DR.KNOWS system introduced and evaluated in the paper.
serenayj/DRKnows
The repository contains training and evaluation code and pretrained-model support for Fusion-in-Decoder models.
facebookresearch/FiD
Official source-code repository linked by the paper for the LeVo song-generation system.
tencent-ailab/songgeneration
Repository containing the LitSearch dataset and code for constructing or evaluating the scientific literature retrieval benchmark.
princeton-nlp/LitSearch
dataset
Repository named IBM/live-api-bench with code for converting BIRD benchmark SQL queries into API call sequences and producing slot-filling and selection-style benchmark outputs.
IBM/live-api-bench
dataset
Repository for the LiveTradeBench platform/package used to run, monitor, and benchmark LLM-based trading agents across U.S. stock and Polymarket environments.
ulab-uiuc/live-trade-bench
package
Contains the LiveVectorLake Python implementation, chunk-level CDC components, Milvus and Delta Lake integrations, query engine, tests, generated test data, benchmark scripts, documentation, and architecture materials.
praj-tarun/LiveVectorLake
dataset
Official repository linked by the paper for access to the LLaMA model family and associated inference resources.
facebookresearch/llama
Repository for the LlamaDuo LLMOps pipeline implementation.
deep-diver/llamaduo
system
Repository for the LLF-Bench environments, installation instructions, wrappers, and task implementations introduced by the paper.
microsoft/LLF-Bench
benchmark
Repository containing the nudging experimental framework, configuration for nudge types and models, and R analysis code for statistical tests and plots.
PapayaResearch/nudging
benchmark
Repository associated with the WORKS 2025 Flowcept Agent materials, including software, synthetic workflow, data, analysis code, query set, and prompts referenced for reproducibility.
flowcept/FlowceptAgent-WORKS25
system
Flowcept code repository used as the provenance capture and observability foundation for the agent architecture and implementation.
ORNL/flowcept
framework
Repository for modernbert_predict_masked.
AnswerDotAI/ModernBERT
Repository for medsam_inference.
bowang-lab/MedSAM
Repository for flowmap_overfit_scene.
dcharatan/flowmap
Repository for esm_fold_predict.
facebookresearch/esm
Repository for stamp_extract_features and stamp_train_classification_model.
KatherLab/STAMP
Public repository for TOOLMAKER code and TM-BENCH benchmark.
KatherLab/ToolMaker
framework
Repository for pathfinder_verify_biomarker.
LiangJunhao-THU/PathFinderCRC
Repository for musk_extract_features.
lilab-stanford/MUSK
Repository for conch_extract_features.
mahmoodlab/CONCH
Repository for uni_extract_features.
mahmoodlab/UNI
Repository for nnunet_train_model.
MIC-DKFZ/nnUNet
Repository for medsss_generate.
pixas/MedSSS
Repository for tabpfn_predict.
PriorLabs/TabPFN
Repository for retfound_feature_vector.
rmaphoh/RETFound_MAE
Repository for cytopus_db.
wallet-maker/cytopus
Repository containing the cross-provider validation framework, SEC 10-K test corpus, synthetic financial database, 480 run traces, reproducibility manifests, and setup instructions for release v0.1.0.
ibm-client-engineering/output-drift-financial-llms
dataset
Repository containing a Python pipeline for extracting LLM uncertainty features, analysing and selecting features, balancing imbalanced data, training calibrated Ridge and XGBoost meta-models, tuning thresholds, and evaluating cost-aware uncertainty models.
ZEFR-INC/lpp-research
framework
Repository containing scripts and source code corresponding to the paper's main experiments, figures, and tables.
slhleosun/reasoning-trajectory
implementation
Official implementation of Chameleon, the plug-and-play compositional reasoning system reproduced and structurally analyzed in the paper.
lupantech/chameleon-llm
Official repository containing the prompts, outputs, token-count materials, and supporting files for the paper's five experiments.
AKSW/AI-Tomorrow-2023-KG-ChatGPT-Experiments
CAMEL is an open-source multi-agent framework for role-playing and agent collaboration.
camel-ai/camel
framework
Code repository for improving factuality and reasoning through multi-agent debate.
composable-models/llm_multiagent_debate
framework
MetaGPT is a multi-agent framework that models a software company using role assignments and SOP-style workflows.
FoundationAgents/MetaGPT
framework
AutoAgents generates different roles for GPTs to form a collaborative entity for complex tasks.
Link-AGI/AutoAgents
framework
Microsoft AutoGen, a framework for building multi-agent AI applications.
microsoft/autogen
framework
Code repository for Solo Performance Prompting / multi-persona self-collaboration.
MikeWangWZHL/Solo-Performance-Prompting
framework
AgentVerse provides task-solving and simulation frameworks for multiple LLM-based agents.
OpenBMB/AgentVerse
framework
ChatDev implements LLM-powered multi-agent collaboration for software development.
OpenBMB/ChatDev
framework
Repository connected to AI Scientist-generated papers reported as having passed peer review at an ICLR workshop.
SakanaAI/AI-Scientist-ICLR2025-Workshop-Experiment
Code repository for MAD, a multi-agent debate framework using large language models.
Skytliang/Multi-Agents-Debate
framework
A curated collection of resources associated with the survey, described by the authors as containing over 200 related papers on agent hallucinations.
ASCII-LAB/Awesome-Agent-Hallucinations
Repository containing code, scripts, data folders, requirements, and reproduction instructions for LLM-DSE: Searching Accelerator Parameters with LLM Agents.
Nozidoali/LLM-DSE
framework
Repository reported by the paper as containing the source code and data for the LLM-BLM study.
youngandbin/LLM-BLM
framework
Repository for reproducing LLM-Explorer experiments and implementation details.
tsinghua-fib-lab/LLM-Explorer
framework
Official repository linked from the paper's project page; it contains the Chat with NeRF/LLM-Grounder implementation, interactive demo code, and notebooks for reproducing the paper's results.
sled-group/chat-with-nerf
Official repository for LLM-Planner. It provides an hlp directory with the high-level prompt generator and kNN dataset from the paper, plus an e2e directory with an end-to-end agent using LLM-Planner.
OSU-NLP-Group/LLM-Planner
Repository for the paper's LLM-REVal framework, including simulation components for LLM-driven research and review workflows.
PlusLabNLP/LLM-REVal
benchmark
Repository containing the LLM-SR code and the generated Oscillation 1, Oscillation 2, and E. coli Growth benchmark datasets.
deep-symbolic-mathematics/LLM-SR
implementation
Repository for BIG-Bench Mistake, including the dataset, prompting materials, annotation guidelines, and released code referenced throughout the paper.
WHGTyen/BIG-Bench-Mistake
dataset
Contains the DELEGATE-52 relay runners, direct and agentic model wrappers, prompts, and 52 domain-specific parsers and evaluators.
microsoft/DELEGATE52
dataset
Official implementation of the Chronos time-series foundation model used for zero-shot inference and sequential fine-tuning.
amazon-science/chronos-forecasting
framework
Configuration files for the CNN-Transformer statistical-arbitrage benchmark replicated in the paper.
gregzanotti/dlsa-public
benchmark
Repository directory containing the IPCA, PCA, and Fama-French residual-return datasets used in the paper's backtests.
gregzanotti/dlsa-public
dataset
Repository for the extensible Judge-Bench collection, shared data schema, prompts, and evaluation code used to compare LLM judgments with human annotations.
dmg-illc/JUDGE-BENCH
benchmark
Official code repository for the paper, containing evaluation scripts, configuration files, a CSV of evaluation results, notebooks, figures, and a modified Lingua training submodule.
brendel-group/llm-line
implementation
Official repository containing the LLMSecEval dataset, code-generation application, and CodeQL-based security-analysis materials introduced and demonstrated in the paper.
tuhh-softsec/LLMSecEval
dataset
Repository for the Needle-In-A-Haystack long-context retrieval test adapted in the paper's fixed- and random-needle experiments.
gkamradt/needle-in-a-haystack
benchmark
Official repository for the LLoCO framework and experiments.
jeffreysijuntan/lloco
framework
Official LongBench repository used for the paper's SingleDoc, MultiDoc, and summarization evaluation; baseline numbers are taken from this repository.
THUDM/LongBench
dataset
Google DeepMind repository containing LMAct environments, expert agents, prompt construction, evaluation code, experiment configuration, and instructions for downloading expert demonstrations.
google-deepmind/lm_act
benchmark
Repository for Local-Splitter, an MCP-compatible and OpenAI-compatible outbound LLM request shim that uses a local small model as a triage layer to reduce cloud token usage.
jayluxferro/local-splitter
system
GitHub repository linked by the paper for LocalEval resources; the repository page inspected stated that available resources were being prepared.
tsinghua-fib-lab/LocalEval
dataset
Public repository for LoCoBench-Agent, including the benchmark framework, evaluation setup, data-download instructions, and metrics for long-context software engineering agent evaluation.
SalesforceAIResearch/LoCoBench-Agent
dataset
Repository containing LogicBench data, evaluation code, and supporting reasoning-chain materials.
Mihir3009/LogicBench
dataset
Public-facing repository for the paper's KD experiments, configuration files, training code, plotting scripts, and geometric feature analysis utilities.
Thegolfingocto/KD_wo_CE
benchmark
Official repository for the LongBench benchmark, datasets, and evaluation code introduced and evaluated in the paper.
THUDM/LongBench
dataset
Repository for the LongMemEval benchmark, evaluation code, history-construction tools, and memory-system experiments.
xiaowu0162/LongMemEval
dataset
Repository containing LongReasonArena benchmark data, input-generation utilities, inference code, and evaluation scripts.
LongReasonArena/LongReasonArena
dataset
Repository containing code, data, and prompts for evaluating LLMs as path planners, including the artifact associated with 'Look Further Ahead: Testing the Limits of GPT-4 in Path Planning'.
MohamedAghzal/llms-as-path-planners
benchmark
Public implementation of the Loquetier virtualized multi-LoRA framework, including kernel source, runtime code, examples, tests, and licenses.
NJUDeepEngine/Loquetier
Repository containing preprocessing code, prompts, configurations, dataset splits, response extraction, and LoRAX load-testing scripts used in the report.
predibase/lora_bakeoff
benchmark
Open-source multi-LoRA inference server using shared base weights, dynamic adapter loading, cross-adapter batching, and adapter-weight caching.
predibase/lorax
Official repository containing the loralib Python package, LoRA integration examples, model checkpoints, and reproduction code for RoBERTa, DeBERTa, and GPT-2 experiments.
microsoft/LoRA
Repository containing the data, curve-fitting code, theory code, and notebooks used to generate the paper's empirical and appendix figures.
KempnerInstitute/loss-to-loss-notebooks
Training code used for the loss-to-loss prediction experiments, including sweep configuration and OLMo-based model training infrastructure.
KempnerInstitute/loss-to-loss-olmo
Official repository containing the paper's QA and key-value datasets, prompt construction code, data-generation scripts, tests, and experiment instructions.
nelson-liu/lost-in-the-middle
Repository for the LoTR method introduced and experimentally evaluated in the paper.
skolai/lotr
Repository for LPS-BENCH containing benchmark examples, mock tools, evaluators, prompt templates, schemas, scripts, and the multi-agent case synthesis pipeline.
tychenn/LPS-Bench
dataset
Repository released for the Lynx hallucination-detection models and HaluBench research artifacts, including code, training data, and model generations.
patronus-ai/Lynx-hallucination-detection
Repository released by the authors for the embedding model family and the paper's model/code/data resources.
FlagOpen/FlagEmbedding
Official repository containing the M3Bench dataset organization, PyBullet and Isaac Sim evaluation workflow, TongVerse setup, task configurations, and instructions for evaluating generated trajectories.
TooSchoolForCool/M3Bench
benchmark
Repository for the general-purpose MadEvolve code-evolution framework with MAP-Elites, island populations, multiple LLM providers, evaluation backends, and analysis tools.
tianyi-stack/MadEvolve
framework
Repository for the Self-Supervised Audio Spectrogram Transformer used as the architectural and empirical baseline for MAE-AST.
YuanGongND/ssast
implementation
Repository for MaGNet containing Python implementation files for MAGE, hypergraph modules, 2D attention modules, training, datasets/model-weight download links, and backtesting.
PeilinTime/MaGNet
dataset
Official code repository for Maieutic Prompting, including tree generation, inference code, benchmark data files, and pre-generated maieutic trees.
jaehunjung1/Maieutic-Prompting
implementation
Repository for the MALLM-GAN method, including the main model code, an Adult-dataset notebook, baseline pipeline, sampling utilities, evaluation utilities, and dependency specifications.
yling1105/MALLM-GAN
implementation
Repository linked by the paper for Mamba model code and pretrained checkpoints.
state-spaces/mamba
Repository containing the ManipulaTHOR environment wrapper, ArmPointNav task and samplers, APND dataset instructions, baseline configurations, actor-critic models, evaluation scripts, and pretrained-model guidance.
allenai/manipulathor
dataset
Repository containing the authors' simulator and market-making agents for scaled beta policy experiments.
JJJerome/rl4mm
framework
Repository for the FOREC/Cross-Market Product Recommendation baseline used for model parameters and comparisons.
hamedrab/FOREC
implementation
Repository linked by the paper for the efficient cross-market recommendation implementation associated with the proposed market-aware models.
samarthbhargav/efficient-xmrec
implementation
Repository released by the authors for Markov Chain of Thought code and associated research artifacts.
james-yw/Markov-Chain-of-Thought
dataset
Repository for MASEval, the framework-agnostic multi-agent system evaluation library introduced and evaluated in the paper.
parameterlab/MASEval
framework
PyTorch/GPU re-implementation of MAE with visualization, pre-training, linear-probing and fine-tuning code, plus pretrained checkpoints used for the paper's reported models.
facebookresearch/mae
implementation
Code repository for the Point-MAE framework introduced and evaluated in the paper.
Pang-Yatian/Point-MAE
implementation
Repository hosting Audio-MAE code and pretrained models for masked spectrogram autoencoding and downstream audio tasks.
facebookresearch/AudioMAE
implementation
Provides code and model assets for MASS pre-training and fine-tuning, including unsupervised and supervised NMT, text summarization, and conversational response generation.
microsoft/MASS
implementation
Repository for the MathCoder family, including inference and evaluation code and links to the MathCodeInstruct dataset and released model checkpoints.
mathllm/MathCoder
Hosts the MathPile project documentation and source-processing code associated with the corpus introduced and evaluated in the paper.
GAIR-NLP/MathPile
dataset
Official MathVista repository containing benchmark data access instructions, evaluation scripts, model-output templates, leaderboard submission resources, and code associated with the paper.
lupantech/MathVista
dataset
Official repository for the MatPlotAgent framework and MatPlotBench benchmark introduced and evaluated in the paper.
thunlp/MatPlotAgent
benchmark
Author-owned repository with ChartQA, FigureQA, PlotQA, and test-file directories for the paper's complex chart-question-answering data.
ChangGuiyong/mChartQA
dataset
Official code repository for running the MDAgents framework and reproducing benchmark experiments across supported medical datasets and LLM backends.
mitmedialab/MDAgents
Official repository for the mDPO method, including an mDPO trainer, Bunny training code, and data links.
luka-group/mDPO
implementation
Sibyl System repository included in the selected AutoGen application sample.
Ag2S1/Sibyl-System
system
AutoTx repository for planning and executing on-chain transactions.
agentcoinorg/AutoTx
GPT-Academic repository for LLM-assisted academic reading, writing, translation, and code/project analysis workflows.
binary-husky/gpt_academic
Composio platform/repository evaluated as a flexible agent application or platform with multiple autonomy-related configurations.
ComposioHQ/composio
h2oGPT repository for private local GPT-style chat and document interaction.
h2oai/h2ogpt
GraphRag_Ollama repository combining AutoGen, GraphRAG, Ollama, and related tooling.
karthikvenkatesan-eaton/Autogen_GraphRAG_Ollama
Langflow platform for building and deploying AI-powered agents and workflows.
langflow-ai/langflow
Letta platform for stateful agents with advanced memory.
letta-ai/letta
AutoGen open-source framework for building AI agent systems using language models, multi-agent conversations, and tool use.
microsoft/autogen
framework
AutoGen Studio application within the AutoGen repository.
microsoft/autogen
system
Dream Team repository for building a team of AI agents with AutoGen.
yanivvak/dream-team
Repository containing the paper's self-ask implementation/demo and released datasets, including materials for Compositional Celebrities and Bamboogle.
ofirpress/self-ask
GitHub source for the multiple-choice Truthful-QA variant used in the model-level ranking experiment.
manyoso/haltt4llm
dataset
CHALE repository used as a hallucination-evaluation dataset with non-hallucinated, half-hallucinated, and hallucinated answer categories.
weijiaheng/CHALE
dataset
Official repository for Measuring Massive Multitask Language Understanding, containing evaluation and calibration code and links to download the test.
hendrycks/test
dataset
Search/RAG infrastructure repository.
devflowinc/trieve
Large language model training framework repository.
EleutherAI/gpt-neox
NLP framework repository.
flairNLP/flair
Glasgow Haskell Compiler repository.
ghc/ghc
Haskell Cabal build/package repository.
haskell/cabal
Transformer model library repository.
huggingface/transformers
Property-based testing library repository.
HypothesisWorks/hypothesis
JavaScript DOM implementation repository.
jsdom/jsdom
Python spreadsheet/data-analysis tool repository.
mito-ds/mito
Machine-learning library repository.
scikit-learn/scikit-learn
JavaScript standard library monorepo.
stdlib-js/stdlib
Official MechAgents repository containing Colab notebooks for the two-agent elasticity and hyperelasticity workflows, the multi-agent linear-elasticity workflow, and the direct two-agent versus multi-agent comparison.
lamm-mit/MechAgents
Repository associated with the paper's Time Series Transformer mechanistic interpretability experiments.
mathiisk/TST-Mechanistic-Interpretability
implementation
Repository for the MedBayes-Lite clinical uncertainty governance layer and associated experimental implementation.
eliashossain001/medbayes-lite
framework
Official repository for the MegaMath dataset project, including released web and code pipeline materials and instructions for accessing dataset variants.
LLM360/MegaMath
dataset
Public codebase for the MELT on-device LLM evaluation system, including PhoneLab and JetsonLab infrastructure, framework integrations, model conversion/evaluation code, prompt analysis, and result parsing.
brave-experiments/MELT-public
Repository containing the official Python implementation of MEME, including code for argument extraction, mode identification/alignment, and training scripts; the README notes that the dataset used in the project is private due to compliance requirements.
gta0804/MEME
framework
Repository for the MeMemo browser-based HNSW retrieval toolkit, documentation, and RAG Playground example application.
poloclub/mememo
framework
Canonical repository for the MemGPT system, now named Letta, implementing stateful LLM agents with persistent memory and related tooling.
letta-ai/letta
Repository for MemR3, the memory retrieval via reflective reasoning controller.
Leagein/memr3
framework
Official open-source implementation of the MemTools framework introduced and evaluated in the paper.
JJJAYYYZhao/MemTools-public
Repository providing data and code for reproducing analyses, with folders for one-dimensional generated regression, two-armed bandit, real-world regression, and an MMLU benchmark.
juliancodaforno/meta-in-context-learning
benchmark
Official project repository for the MetaGPT framework introduced and evaluated in the paper.
geekan/MetaGPT
implementation
Repository containing the MetaOptimize implementation, package files, example usage, and experiment code for CIFAR10, ImageNet, TinyStories, and continual CIFAR100 experiments.
sabersalehk/MetaOptimize
framework
Official MetaTool repository containing ToolE data, tool descriptions and embeddings, scenario lists, prompt templates, model-generation scripts, and evaluation code.
HowieHwong/MetaTool
benchmark
Public implementation companion containing the intent-to-specification pre-experiment stage, SevenNet-based experiment utilities and MCP server scripts, and discussion, revision, CLI, and Streamlit interface components.
IMMS-Ewha/MIND
Official repository for the Mind2Web dataset, benchmark processing and evaluation resources, and MindAct fine-tuning and model code.
OSU-NLP-Group/Mind2Web
dataset
Contains the released evaluation code, Graphviz-based synthetic mind-map generator, crawled and synthetic annotation preparation tools, and links to the benchmark datasets.
MiaSanLei/MindBench
benchmark
Repository linked by the paper for the MindWatcher agent framework, models, benchmark resources, and related implementation artifacts.
TIMMY-CHAN/MindWatcher
framework
Repository for MiniCheck code, model usage, synthetic data generation code, benchmark evaluation demo, and links to LLM-AggreFact and Hugging Face model resources.
Liyan06/MiniCheck
benchmark
Repository for the Minions communication protocol enabling small on-device models to collaborate with frontier cloud models.
HazyResearch/minions
system
Official repository for reproducing MINT evaluation, benchmark data, prompts, and supporting code.
xingyaoww/mint-bench
dataset
Code repository for the MISS generative medical VQA framework and its training approach.
TIMMY-CHAN/MISS
implementation
Repository containing the paper's mKG-RAG implementation and associated resources.
xandery-geek/mKG-RAG
framework
MedicalZooPytorch repository used in the benchmark's OOD training set.
black0017/MedicalZooPytorch
Text classification repository listed as TCL in the benchmark's OOD training repositories.
brightmart/text_classification
DeepFloyd IF repository used for multi-modal image tasks.
deep-floyd/if
Deep Graph Library repository used for graph-model tasks.
dmlc/dgl
framework
PyTorch-GAN repository used for image-GAN tasks.
eriklindernoren/PyTorch-GAN
ESM repository used for protein/biomedical tasks.
facebookresearch/esm
Public ML-Bench code and benchmark resources released by the paper.
gersteinlab/ML-bench
dataset
BERT repository used for ML-Bench tasks.
google-research/bert
PyTorch Image Models repository used as an OOD evaluation repository.
huggingface/pytorch-image-models
Grounded Segment Anything repository used as an OOD evaluation repository.
IDEA-Research/Grounded-Segment-Anything
Muzic repository used for music/audio tasks.
microsoft/muzic
OpenCLIP repository used for multi-modal tasks.
mlfoundations/open_clip
vid2vid repository used for video tasks.
NVIDIA/vid2vid
OpenDevin agent framework evaluated in ML-Agent-Bench with GPT-4o, GPT-4, and GPT-3.5.
OpenDevin/OpenDevin
system
LAVIS repository used for multi-modal tasks.
salesforce/lavis
framework
Stable Diffusion repository used in the benchmark's OOD training set.
Stability-AI/stablediffusion
Tensor2Tensor repository used in the benchmark's OOD training set.
tensorflow/tensor2tensor
Time-Series-Library repository used for time-series tasks.
thuml/Time-Series-Library
Learning3D repository used for 3D vision tasks.
vinits5/learning3d
External-Attention-pytorch repository used for attention-use tasks.
xmu-xiaoma666/External-Attention-pytorch
Official code repository for MLAgentBench, including benchmark tasks, environment, agent implementations, runners, and evaluation scripts.
snap-stanford/MLAgentBench
benchmark
Repository for the benchmark and evaluation resources introduced by the paper.
chchenhui/mlrbench
dataset
Repository for mMARCO with translation scripts, dataset access information, retrieval instructions, and released fine-tuned model references.
unicamp-dl/mMARCO
dataset
Official MMDT source repository with scripts and framework components for evaluating text-to-image and image-to-text models across the six trustworthiness perspectives.
AI-secure/MMDT
Official repository containing inference and evaluation code, setup instructions, and links to the released dataset and leaderboard.
Alpha-Innovator/MME-Reasoning
dataset
Official repository for the MMIR-TCM framework and its associated MedTCM and TDEU artifacts.
jw-chae/MMIR-TCM
Repository for the MMReason benchmark, with citation and evaluation instructions and integration through VLMEvalKit.
HJYao00/MMReason
dataset
Official XiaoMi repository for Mobile-Bench, including Appium/emulator setup materials, API/UI agent code folders, data/result directories, prompts, requirements, and README instructions.
XiaoMi/MobileBench
dataset
Repository for MobileAgentBench, an automated benchmark for mobile LLM agents with a Python library and default tasks using SimpleMobileTools apps.
MobileAgentBench/mobile-agent-bench
benchmark
Repository named Modalitites-Impact-In-ML under the belgats GitHub account. It was public but empty when accessed.
belgats/Modalitites-Impact-In-ML
implementation
Public Python repository containing MODE ingestion and inference code, clustering and centroid-routing components, benchmark scripts, evaluation data and logs, tests, and documentation.
rahulanand1103/mode
framework
Official Model Context Protocol server collection used to identify official and community MCP integrations.
modelcontextprotocol/servers
Replication package released by the authors for the MCP server empirical study.
SAILResearch/replication-25-mcp-server-empirical-study
dataset
Public repository containing the paper's collected landscape data and implementation examples.
security-pride/MCP_Landscape
dataset
Python/TensorFlow implementation of Robust Log-Optimal Strategy with Reinforcement Learning discussed as a policy-based portfolio optimization approach.
fxy96/Robust-Log-Optimal-Strategy-with-Reinforcement-Learning
framework
Python/TensorFlow implementation of the PGPortfolio or EIIE-style portfolio reinforcement learning framework discussed in the survey.
ZhengyaoJiang/PGPortfolio
framework
GitHub repository for the SYMBA crypto multi-agent reinforcement learning market simulator.
johannlussange/symba_crypto
framework
Official implementation repository for the ModuleFormer architecture, with inference code and links to released MoLM model weights.
IBM/ModuleFormer
implementation
The Megatron-DeepSpeed repository is explicitly linked as the DeepSpeed implementation used as the principal large-scale MoE comparison baseline.
microsoft/Megatron-DeepSpeed
PaddleFleetX is the open-source architecture on which MoESys is implemented and is benchmarked against Megatron-LM in the platform comparison.
PaddlePaddle/PaddleFleetX
Repository for the MonkeyOCR model family, including inference code, deployment instructions, model links, benchmark materials, and a dated announcement for the MonkeyOCR v1.5 technical report.
Yuliang-Liu/MonkeyOCR
implementation
Repository containing the paper's fine-tuning, inference, plotting, and experiment configuration code for intrinsic moral reward training of LLM agents.
liza-tennant/LLM_morality
Repository for the GroundMoRe dataset workflow and MoRA training, fine-tuning, checkpoint conversion, and evaluation code.
dengandong/GroundMoRe
Repository for the mPLUG-DocOwl model family and the paper's released code, models, training data, and evaluation resources.
X-PLUG/mPLUG-DocOwl
implementation
Synthetic train, development, and test files used for the paper's arithmetic argument-extraction experiments.
AI21Labs/MRKL_synthetic_data
dataset
TensorFlow Datasets implementation for distributing the MT-Opt robot-episode and success-detector datasets associated with the paper.
tensorflow/datasets
dataset
Auto-GPT is discussed as an autonomous AI application whose main agent, plugins, memory, file access, internet access, code execution, image generation, and oracle-like functions can be represented within the proposed multi-agent graph framework.
Significant-Gravitas/Auto-GPT
framework
BabyAGI is discussed as an AI agent system with task creation, prioritisation, and execution chains that can be modelled as interconnected agents plus a vector-database plugin.
yoheinakajima/babyagi
system
Official source-code repository for the paper, including scalar and two-dimensional consensus experiments, topology configuration, plotting utilities, and experiment execution code.
WindyLab/ConsensusLLM-code
Official data release containing generated experiment outputs for the agent-count, temperature, and personality analyses.
WindyLab/ConsensusLLM-code
Repository associated with the experiment in which a fine-tuned Llama 2 7B Chat model attempts to manipulate an LLM overseer or reward model, with RL increasing jailbreak attempts.
AlexMeinke/fooling-the-overseer
implementation
Repository associated with the experiment that repeatedly rewrites news articles using LLMs and evaluates degradation in factual accuracy.
qfeuilla/DistordedNews
implementation
Repository associated with the experiment testing whether specialized LLM driving agents fine-tuned on different traffic conventions fail to coordinate when yielding to an emergency vehicle.
SUMEETRM/driving_llms
implementation
Official X-VLM repository containing PyTorch pre-training and fine-tuning code, task configurations, data-format examples, and links to pre-trained and fine-tuned checkpoints.
zengyan-97/X-VLM
Official MH-MoE implementation based on TorchScale and fairseq, including setup and pretraining scripts.
yushuiwx/MH-MoE
implementation
Repository created to support the survey by collecting and categorizing relevant research papers, datasets, application scenarios, framework figures, and future-direction materials on value alignment in agentic AI systems.
Wei-ZENG1020/Value-Alignment-Agentic-AI-Papers-Survey-Taxonomy
Repository containing the Multi-LogiEval data and associated evaluation or reasoning-chain artifacts.
Mihir3009/Multi-LogiEval
dataset
GitHub repository made available by the authors for MMTB.
yupeijei1997/MMTB
dataset
Source code and experiment framework for the paper, including MGDA-UB/min-norm solvers and MultiMNIST-related code/data.
isl-org/MultiObjectiveOptimization
Repository containing the official implementation of Agentic Predictor for multi-view performance prediction in LLM-based agentic workflows.
DeepAuto-AI/agentic-predictor
system
Public repository for the MARBLE framework and MultiAgentBench code and data used to develop, test, and evaluate LLM-based multi-agent systems.
MultiagentBench/MARBLE
dataset
Repository identified by the paper as containing the project, data, Python code, ontology model, mapping rules, hyperparameter tuning code for ComplEx, TransE, and DistMult, and code to train and predict using TransE.
durgeshnandini/Multidimensional-Knowledge-Graph-Embeddings-for-International-Trade-Flow-Analysis
dataset
Repository for reproducing baseline generation, citation generation, MuRGAt-Score evaluation, and program-aided generation experiments.
meetdavidwan/murgat
benchmark
Official code and model workflow for preprocessing SIMMC 2.0 images, ITM and BTM pretraining, task-specific training, and challenge evaluation.
rungjoo/simmc2.0
Repository containing MedTok training and inference code, dataset preparation folders, EHR and medical-QA tutorials, environment configuration, and links to released token embeddings.
mims-harvard/MedTok
A constantly updated paperlist related to the survey topic of multimodality representation learning.
marslanm/multimodality-representation-learning
Public repository containing modules that form MRT and utility code used for data piping in the paper's experiments.
EgoPer/Multiple-Resolution-Tokenization
implementation
Toolkit and repository for creating, sharing, and materializing the natural-language prompt templates used to build P3 and train T0.
bigscience-workshop/promptsource
Code and instructions for reproducing T0 training, evaluation, inference, and ablation checkpoints.
bigscience-workshop/t-zero
Official author repository containing MuSiQue data download utilities, evaluation scripts, released predictions, trained-model utilities, and code/configurations for the paper's experiments.
stonybrooknlp/musique
dataset
LASSO is a platform for scalable software code analysis and observation, combining dynamic and static program analysis, code search, N-version assessment, automated test generation, software experimentation, and benchmarking.
SoftwareObservatorium/lasso
framework
Source code used for the N^2M^2 paper, including training and evaluation scripts, robot environments, task wrappers, Gazebo assets, and instructions for PR2, HSR, and TIAGo experiments.
robot-learning-freiburg/mobile-rl
Supplemental repository containing accepted submissions, the call for papers, nanopublication files, the questionnaire, and visualization materials for the field study.
LaraHack/formalization_papers_supplemental
Repository containing the nanopublication collection and graph assets used to analyze and visualize the formalization-paper special-issue workflow.
LaraHack/fpsi_analytics
Repository for Nanobench, the template-driven interface used by participants to create formalizations, class definitions, submissions, reviews, responses, updates, and decisions as nanopublications.
peta-pico/nanobench
Repository for Tapas, the generic triple-store interface used to run template-based SPARQL queries and display submission and review overviews.
peta-pico/tapas
Repository providing an open-source NRT-style training recipe built on top of verl, including scripts and configuration for NRT training.
sharkwyf/native-reasoning-models
framework
CodRep dataset/competition artifact for code refinement and defect detection.
ASSERT-KTH/CodRep
dataset
BigCloneBench dataset for clone detection and related code-understanding tasks.
clonebench/BigCloneBench
dataset
Code Contests dataset for code generation from competitive-programming problems.
deepmind/code_contests
dataset
InCoder repository for generative code models.
dpfried/incoder
implementation
Description2Code dataset for mapping descriptions to code.
ethancaballero/description2code
dataset
CodeSearchNet dataset covering multiple programming languages for code search and code-language tasks.
github/CodeSearchNet
dataset
APPS benchmark for code generation from programming problems.
hendrycks/apps
benchmark
Project CodeNet dataset for program understanding, generation, and refinement tasks.
IBM/Project_CodeNet
dataset
Copilot for Xcode source editor extension integrating GitHub Copilot and ChatGPT-style functions into Xcode.
intitni/CopilotForXcode
system
CodeXGLUE benchmark for multiple code intelligence tasks.
microsoft/CodeXGLUE
dataset
PyCodeGPT/CERT-related repository for Python code generation.
microsoft/PyCodeGPT
implementation
xCodeEval/ExecEval repository for multilingual code evaluation tasks.
ntunlp/xCodeEval
benchmark
HumanEval benchmark for evaluating code-generation models.
openai/human-eval
benchmark
WikiSQL dataset for SQL generation/summarization-style tasks in the paper's table.
salesforce/WikiSQL
dataset
CONCODE dataset for mapping natural language and program context to code.
sriniiyer/concode
dataset
Code-LMs repository associated with PolyCoder and code-language-model research.
VHellendoorn/Code-LMs
implementation
Official implementation repository for the expanded Natural Language Reinforcement Learning project, including shared NLRL libraries and later Maze, Breakthrough, and Tic-Tac-Toe experiments.
waterhorse1/Natural-language-RL
Python code for collecting LLM ranking data, training the scoring model, and training policies with direct-score or potential-difference rewards.
sy-shi/RLAIF_ScoreDiff
implementation
GroundHog is the authors' Theano-based recurrent neural network framework containing the neural machine translation implementation used for the paper.
lisa-groundhog/GroundHog
Repository released by the authors for Multimodal-ZeroShotTM, Multimodal-Contrast, and the multimodal topic modeling experiments.
gonzalezf/multimodal_neural_topic_modeling
benchmark
Repository for NNHedge, containing components for simulated instruments, neural hedging models, data loading, training, and assessment.
guijinSON/NNHedge
framework
Author-linked reference implementation of NSR, including SVD compression, TaskKnowledgeBank logic, allocation policies, dataset builders, experiment runners, and visualization code.
bhyoon-me/nsr
Repository containing code for persona vector generation, the user-study interface, and user-study analysis associated with the neural transparency paper.
mitmedialab/neural-transparency
system
Repository containing code, data folders, source files, scripts, requirements, and usage instructions for running CaRing and evaluating ProofWriter, GSM8K, and PrOntoQA experiments.
DAMO-NLP-SG/CaRing
framework
Repository for the Next-Generation LLM for UAV system, including the main application, short-, medium-, and long-range route-planning utilities, path-planning utilities, control-platform utilities, examples, and integrated data folders.
liangqiyuan/NeLV
framework
Repository cited as the source of the Azure LLM inference production trace used to construct a dynamic request-rate workload.
Azure/AzurePublicDataset
dataset
The repository contains classifier, data/query, notebook, red_lm, and target_lm components plus training code; its README states that supervised-learning code is on the master branch and RL training is on the feature/ppo branch.
anugyas/NLUProject
The repository describes NormCode as a language for auditable multi-step AI workflows, lists core components such as infra, canvas_app, cli_orchestrator.py, documentation, and examples, and links to the arXiv paper.
lys5588/Normcode-paper
framework
The fairseq NormFormer example provides architecture flags and causal-language-model training commands corresponding to the paper.
facebookresearch/fairseq
implementation
Official repository for NOSA and NOSI, including the attention implementation, NOSI package, environment instructions, benchmark scripts, and links to released NOSA-1B, NOSA-3B, and NOSA-8B models.
thunlp/NOSA
Official PyTorch implementation of the paper's layer-wise expert pruning, progressive pruning, and dynamic expert skipping methods.
Lucky-Lance/Expert_Sparsity
Repository containing code and configuration for training and inference of Qwen3 8B, DeepSeek LLM 7B, and LLaMA3 8B Instruct on financial sentiment datasets, including preprocessing, model configuration, training, inference, and evaluation.
NLPforFinance/fine-tuning-of-lightweight-large-language-models
implementation
Repository containing demonstrations and scenarios for indirect prompt-injection attacks, including synthetic GPT-based applications and attack examples discussed in the paper.
greshake/llm-security
Open-source GPT-Researcher framework used as the fixed deep research execution pipeline and unpruned baseline on which pruning variants are implemented.
assafelovic/gpt-researcher
Repository whose README cites the NumHTML AAAI 2022 paper and states that code and data used for the paper are provided.
YangLinyi/HTML-Hierarchical-Transformer-based-Multi-task-Learning-for-Volatility-Prediction
dataset
Official repository for O-Researcher, including model serving, web-search and crawl-page tools, inference code, deployment scripts, and links to released SFT/RL models and datasets.
OPPO-PersonalAI/O-Researcher
Official repository for the Oasis data-curation and assessment system introduced by the paper.
tongzhou21/Oasis
Repository containing the paper's Off-Policy Corrected Reward Modeling implementation and the code and resulting data for filtering the short Alpaca-Farm setting.
JohannesAck/OffPolicyCorrectedRewardModeling
implementation
AutoGen repository into which the paper states AgentOptimizer was integrated.
microsoft/autogen
Official repository for the OLMoE paper, linking the released model, data, code, logs, configurations, and related resources.
allenai/OLMoE
Repository for the Omanic benchmark and associated experimental implementation.
XiaojieGu/Omanic
dataset
Repository for the ACL 2025 OMGM coarse-to-fine multimodal retrieval and RAG framework.
ChaoLinAViy/OMGM
framework
Repository for the OmniCode benchmark code and data.
seal-research/OmniCode
dataset
Repository associated with the paper's implementation of probabilistic monolithic and model reconciling explanation algorithms.
YODA-Lab/Probabilistic-Monolithic-Model-Reconciling-Explanations
benchmark
Repository stated by the paper as containing code to reproduce the experiments for the uncertainty-measure framework.
ml-jku/uncertainty-measures
implementation
Repository linked by the paper as the code for the controlled shortest-path reasoning experiments.
riccardoalberghi/DP
benchmark
Public ReAct repository used as the source code-base for the original ReAct setup and corresponding experiments.
ysymyth/ReAct
framework
Repository containing the RepoExec benchmark/source code for executable repository-level code generation evaluation and related dependency-utilization tooling.
FSoft-AI4Code/RepoExec
dataset
Repository containing code for the paper, including configurations for BM25 baseline, ReAct agent variants, self-reflection, AutoCodeRover-related settings, and evaluation scripts.
JetBrains-Research/ai-agents-code-editing
benchmark
Repository containing the ARC task data and supporting materials for the benchmark introduced and analyzed in the paper.
fchollet/ARC
dataset
Code repository for the paper's SimpleLogic experiments and constructive BERT reasoning implementation.
joshuacnf/paradox-learning2reason
Microsoft's TorchScale repository exposes X-MOE as a configurable sparse-MoE feature and includes this paper in its citation list.
microsoft/torchscale
implementation
Repository containing AutoTransform, AutoInject, Challenger/Inspector defenses, experiments, figures, and benchmark resources for the paper.
CUHK-ARISE/MAS-Resilience
Repository for the paper's PyTorch implementation, including scripts, prompts, helper functions, and instructions for running memory representation and retrieval experiments.
zengrh3/StructuralMemory
dataset
Repository for the paper's model preparation, device-specific conversion and deployment, unified inference measurement, power parsing, and benchmark result artifacts.
PINetDalhousie/EdgeAI-Sustainability
Official ToolBench repository containing benchmark tasks, action-generator and evaluator code, tests, setup instructions, and evaluation commands.
sambanova/toolbench
benchmark
Repository path for Agent Spec runtime adapters that translate Agent Spec components into framework-specific equivalents for popular agentic frameworks.
oracle/agent-spec
implementation
WayFlow is presented as the paper's reference runtime for executing Agent Spec components, including native support for Agent Spec Agents and Flows.
oracle/wayflow
framework
Repository announced by the authors for code and data supporting the neutral event graph induction framework.
liusiyi641/Neutral-Event-Graph
dataset
Open-source code and data repository for the OpenAgentSafety framework and benchmark task suite.
Open-Agent-Safety/OpenAgentSafety
dataset
Official implementation repository for OpenAI Gym, the reinforcement-learning environment toolkit introduced and described by the paper.
openai/gym
OpenAI Evals implementation for measuring language-model text compression and decompression behavior, including the possibility of hiding information in compact strings.
openai/evals
Repository linked by the authors as the location of all generated code and other answers used in the study.
lmous/openai-gpt4-coding-assistant
implementation
OpenAssistant's open-source repository containing the project code, data-collection application components, guidelines/configuration, and model-training implementation associated with OASST1.
LAION-AI/Open-Assistant
dataset
The open-source implementation of the OpenHands platform introduced and evaluated in the paper.
All-Hands-AI/OpenHands
Meta AI's metaseq repository contains the codebase used to train and experiment with OPT models, including OPT-specific project materials.
facebookresearch/metaseq
A modular, parallelized code base for simulating constant-product AMM trading against a CEX, designed for large-scale experiments and extensible market-design variants.
JasonSome/cpmm-trading
implementation
Library of ADMM applications for sparse and low-rank optimization used to test NewADMM.
canyilu/LibADMM
package
Huawei Cloud VM-placement traces used in the cloud resource scheduling case study.
huaweicloud/VM-placement-dataset
dataset
Official implementation of OCTree for optimized feature generation for tabular data via LLMs with decision-tree reasoning.
jaehyun513/OCTree
framework
Official repository linked by the paper for the ORACLE framework introduced and evaluated in the study.
yangzhj53/ORACLE
Open-source MA-Gym codebase for evaluating Manager Agents in graph-based multi-agent workflow orchestration.
DeepFlow-research/manager_agent_gym
framework
Open-Finance-Lab AgenticTrading is an open-source experimental playground for LLM-powered trading agents, backtests, paper-trading simulations, reasoning logs, benchmark comparisons, and the FinAgent orchestration subsystem.
Open-Finance-Lab/AgenticTrading
framework
Repository for the OrderFusion model and workflow, including package installation, tutorial notebook, data-reading, model optimization, evaluation, and forecast-plotting functions.
runyao-yu/OrderFusion
package
Repository for Orla, the library and execution engine for constructing and serving LLM-based agentic workflows with stage mapping, orchestration, and workflow-level memory management.
dorcha-inc/orla
framework
Official implementation of PaCA, including a modified PEFT library and examples for task-specific fine-tuning, instruction tuning, NVIDIA GPUs, and Intel Gaudi HPUs.
WooSunghyeon/paca
Official PackKV repository containing custom C++/CUDA extensions, model integrations, evaluation code, scripts, and reproducibility commands.
BoJiang03/PackKV
Open-source repository for the pAI/MSc research agent and workflow described in the technical report.
PoggioAI/PoggioAI_MSc
Claude Code Skill companion for PoggioAI/MSc.
PoggioAI/PoggioAI_MSc-claude
Official Uber Research repository containing implementations of the original POET and Enhanced POET algorithms.
uber-research/poet
Official Palu implementation with compression and Fisher rank-search code, perplexity and zero-shot evaluation, LongBench evaluation, and attention/reconstruction latency kernels.
shadowpa0327/Palu
Public source-code repository for PAMS, the Python-based Platform for Artificial Market Simulations.
masanorihirano/pams
framework
Official code artifact for the paper, including the PEFT/S4 adapter configuration and an example command for evaluating it with a RoBERTa backbone on GLUE.
amazon-science/peft-design-spaces
Repository containing BART and T5 training code, LoRA components, layer-retention configurations, dataset preprocessing scripts, and experiment configuration files for the paper.
zhuyunqi96/LoraLPrun
Repository for the RedPajama data recipe and corpus from which the paper draws compute-dependent pretraining subsets.
togethercomputer/RedPajama-Data
dataset
Author repository containing code and instructions to reproduce the BERT passage re-ranking experiments on MS MARCO and TREC-CAR.
nyu-dl/dl4marco-bert
Open-source implementation of the 2D odd-one-out environments whose basic, confounded, and experimenting/meta-learning variants are used and adapted in the paper's passive-agent experiments.
deepmind/tell_me_why_explanations_rl
PathBench contains shared implementations and configurations for WSI-Caption, HistGen, BiGen, and SCOUT, fixed report splits, conventional NLG metrics, and dataset-specific CRQS pipelines.
surykntsingh/PathBench
benchmark
Repository provided by the authors to support reproduction of the Identifier-Organizer-Adapter data synthesis and distillation framework.
BokwaiHo/IOA
framework
Official open-source repository for the PedNStream pedestrian-network simulator, including core LTM modules, scenario data, examples, visualization, tests, and configuration files.
WaimenMak/PedNStream
Official ParlAI repository containing the Persona-Chat task infrastructure and associated dialogue-model resources.
facebookresearch/ParlAI
Code used to scrape and process the dataset, construct train/test and benchmark datasets, and build and evaluate baseline phishing detection models.
phreshphish/phreshphish
dataset
PKU-Alignment's Safe-RLHF/Beaver repository implements SFT, reward/cost modeling, RLHF, and SafeRLHF and explicitly announces/releases the PKU-SafeRLHF dataset family through its project resources.
PKU-Alignment/safe-rlhf
Repository linked by the paper for the updated PlanBench benchmark, including tools, datasets, prompt/result reproduction scripts, planning utilities, and the PlanBench implementation.
karthikv792/LLMs-Planning
dataset
CMBAgent Benchmarks repository used for CAMB tool-grounded precision tasks.
cmbagent/Benchmarks
dataset
Repository containing the implementation of the Point-M2AE hierarchical point-cloud pre-training framework.
ZrrSkywalker/Point-M2AE
implementation
Official codebase for Policy Decorator, including offline base-policy training and online residual-refinement scripts for ManiSkill and Adroit configurations.
tongzhoumu/policy_decorator
Agent Network Protocol is treated as an open-network agent discovery and collaboration protocol using decentralized identifiers and JSON-LD.
agent-network-protocol/AgentNetworkProtocol
Model Context Protocol is treated as a standardized context-ingestion and tool-invocation protocol relevant to execution-level transitions.
modelcontextprotocol
Official repository released by the authors for the paper's post-training calibration experiments and PosConf method.
EIT-NLP/Post-Training-Calibration
Contains framework code, domain profiles, prompt builders, placeholder QA, deterministic replacement, paired full-resolution benchmark posters, evaluation outputs, runtime and failure audits, prompts, manifests, and configuration records.
tyy99phy/paper_poster_harness
Repository associated with the paper's dataset and experimental framework for evaluating LLM-generated scientific reviews against human reviews and post-publication outcomes.
akhilpandey95/LMRSD
dataset
Repository containing code for the paper, including PhraseBank preprocessing, training, and testing scripts for the LLaMA financial sentiment analysis experiments.
luosting/LLaMA-Financial-sentiment-analysis
implementation
Open-source code for the Hypothetical Document Embeddings retrieval method introduced and evaluated in the paper.
texttron/hyde
Apache Airflow repository; used as an example among ten large open-source industrial projects from which function-summary pairs were sampled.
apache/airflow
RxJava repository; used as an example among ten large open-source industrial projects from which function-summary pairs were sampled.
ReactiveX/RxJava
Official repository containing the raw Provo data used by the study, generation scripts and saved model continuations, uncertainty estimates, joint analysis notebooks, semantic and syntactic TVD experiments, and appendix experiments.
evgeniael/predict_next_word
Repository released by the authors for Step Law experimental code, data/configuration artifacts, and model checkpoints.
step-law/steplaw
Original StockNet codebase for stock movement prediction from tweets and historical prices.
yumoxu/stocknet-code
benchmark
Repository for the StockNet dataset, containing historical stock-price data and tweet-data structure for stock movement prediction from tweets and historical prices.
yumoxu/stocknet-dataset
dataset
Repository reported by the paper as the source code for the LLM-enhanced tweet emotion analysis and stock movement prediction framework.
anv0101/stock-prediction
implementation
LLT R package used by the authors to transform the cryptocurrency datasets before classifier evaluation.
mtkurbucz/LLT
package
A Python benchmark for backtesting prediction-market trading agents using real Kalshi market replay data, included episodes, agent interfaces, simulator configuration, and metrics output methods.
Oddpool/PredictionMarketBench
dataset
Official code repository for the prefix-tuning method and experiments introduced by the paper.
XiangLi1999/PrefixTuning
Repository containing the generated historical_traffic_data.csv dataset, location.py simulation code, and HTML traffic-map and prediction visualizations used by the paper.
Psxxg/Fairly-Private
Repository containing the ProAgent code, environment setup, experiment scripts, prompt/agent implementation, and instructions for reproducing the Overcooked-AI evaluations.
PKU-Alignment/ProAgent
Official implementation repository for ProAgent, the LLM-based agent system introduced by the paper for Agentic Process Automation.
OpenBMB/ProAgent
framework
Official codebase containing prompt templates, model/evaluation utilities, scripts to reproduce figures and significance tests, a NiceGUI corpus visualization app, and download links for the OEDD v1.0.0 test corpus and initial results.
sonnygeorge/OEDD
dataset
Public code repository for the trajectory-probing experiments and analyses introduced in the paper.
AndresAlgaba/probing_reasoning_traces
benchmark
Repository containing task templates, benchmark-generation scripts, preprocessing, model-prediction configurations, response extraction, and evaluation code for reproducing and extending the ProcBench experiments.
ifujisawa/proc-bench
benchmark
Repository containing code, prompts, and data for reproducing or evaluating Program of Thoughts prompting.
wenhuchen/Program-of-Thoughts
benchmark
Official repository containing generated self-play data, fine-tuning datasets, evaluation directories, notebooks, and supporting code for the SInQ experiments.
Avmb/semantic_neq_game
Official repository location for the MBPP programming-problem benchmark introduced by the paper.
google-research/google-research
dataset
Notebook implementing the MathQA-to-Python translation and generation workflow used for MathQA-Python.
google/trax
implementation
Official ProgramBench repository for the benchmark, tooling, usage guide, and baseline evaluation workflow.
facebookresearch/ProgramBench
dataset
Repository containing the progressive multimodal search-agent rollout, image and text tools, retrieval and summarization services, TN-GSPO modifications, training scripts, evaluation scripts, and dataset configuration files.
DingWu1021/Promsa
framework
Official ProtAgents repository containing the agent implementation, shared functions, ProteinForceGPT integration code, configuration utilities, and notebooks corresponding to Experiments I, II, and III.
lamm-mit/ProtAgents
Repository for the paper's trace-rewriting experiments, including configuration files, source scripts for trace generation, rewriting, distillation and evaluation, prompt-optimization scripts, and pre-generated GSM8K/MATH rewritten trace datasets.
xhOwenMa/trace-rewriting
dataset
Repository for SimpleVLA-RL, a reinforcement-based VLA approach that uses online learning with a binary reward and a single demonstration trajectory.
PRIME-RL/SimpleVLA-RL
Repository released by the authors for the PuzzleVQA benchmark, including the research artifact supporting dataset generation and evaluation.
declare-lab/LLM-PuzzleTest
dataset
Repository for evaluating LLM agents on real-world coding tasks, with benchmark code, configuration, data folders, unit-test workflow, PyInstruct data link, and PyLlama3 model link.
Mercury7353/PyBench
dataset
Repository containing the public implementation and data-processing pipeline associated with the paper.
DARE-ML/DeepGR4J-Extremes
framework
Repository containing Qlib's code, documentation, and additional platform features beyond those described in the paper.
microsoft/qlib
framework
Official QLoRA implementation and training code released by the paper authors.
artidoro/qlora
implementation
bitsandbytes library containing low-bit quantization and CUDA components used to implement QLoRA's 4-bit training stack.
TimDettmers/bitsandbytes
Repository maintaining QMSum data, train/validation/test splits, domain-specific data folders, extracted spans, model outputs, figures, and a data-processing notebook.
Yale-LILY/QMSum
dataset
Official implementation and reproducibility artifact for QSpec, including installation instructions, Docker support, compiled kernels, experiment scripts, and vLLM-related code.
hku-netexplo-lab/QSpec
Python and shell-script repository containing QTMRL or multi-indicator experiment code, non-multi-indicator model scripts, baseline scripts, dependency specifications, and instructions for downloading a related multi-indicator dataset.
ChenJiahaoJNU/QTMRL
framework
Code and example workflow for EcoDatum's operator outputs, labeling functions, LabelModel ensemble, configuration, and curated JSONL generation.
haomo-ai/EcoDatum
Repository containing paper versions, an overview image, README, and Jupyter Notebook implementation for Quantformer.
zhangmordred/QuantFormer
implementation
Repository cited for GPT-J-6B, the 6B autoregressive language model evaluated as the largest model in the paper's main Pile-based scaling experiments.
kingoflolz/mesh-transformer-jax
Repository containing code and data supporting the RAG application, custom probes and detectors, Garak configuration, synthetic PII data, and thesis experiments.
rhmoult/DSU
Repository containing code, data, model implementations, visualisations, and setup instructions for classic and quantile versions of linear regression, BD-LSTM, Conv-LSTM, and ED-LSTM across BTC, ETH, Sunspot, Mackey-Glass, and Lorenz datasets.
sydney-machine-learning/quantiledeeplearning
dataset
Official Quark implementation with separate branches for toxicity unlearning, sentiment steering, and repetition reduction, plus evaluation scripts and released checkpoint links.
GXimingLu/Quark
Contains the contextual chunker, embedding and reranker training code, Kaggle submission notebooks, official competition data layout, and experiments corresponding to the baseline and final system.
nuinashco/unlp2026_shared_task
system
Official repository for the Qwen-VLA model and technical report, containing project information, demonstrations, and reported benchmark summaries.
QwenLM/Qwen-VLA
Official repository for the Qwen3 Embedding and Qwen3 Reranker research artifacts introduced in the paper.
QwenLM/Qwen3-Embedding
Official Qwen3 repository associated with the model family introduced in the report.
QwenLM/Qwen3
LMFlow contains the paper's RAFT alignment implementation, including a run_raft_align.sh example and diffusion demonstrations.
OptimalScale/LMFlow
Adrian H. Raudaschl's RAG-Fusion repository, cited by the paper as the implementation/artifact context for the RAG-Fusion workflow.
Raudaschl/RAG-Fusion
Repository containing the RAGSmith codebase and the datasets used in the study.
yAquila/RAGSmith
dataset
Repository released by the authors containing the SGLang-based implementation of RLT and LBGR together with scripts and configurations for reproducing the GSP, ShareGPT, UltraChat, and Loogle evaluations.
fzwark/KVRouting
Author-maintained repository containing Python and MATLAB implementations and examples for randomizing affine-diffusion models and computing randomized characteristic-function constructions.
LechGrzelak/Randomization
implementation
Repository associated with Rational Tuning experiments for LLM cascade modeling and threshold optimization.
mzelling/rational-llm-cascades
implementation
Official repository containing the RDMA implementation and the datasets generated or analyzed for the study.
jhnwu3/RDMA
Official RE-Bench repository containing the seven task families and supporting setup material used to evaluate autonomous AI R&D capabilities.
METR/RE-Bench
benchmark
Public implementation of the Modular agent scaffold used as one of the two main agent designs in RE-Bench experiments.
poking-agents/modular-public
Open-source AIDE machine-learning engineering agent, lightly adapted as the second main scaffold evaluated in RE-Bench.
WecoAI/aideml
Alpaca Eval is one of the two central input sets compared in the paper's automatic bencher experiments.
tatsu-lab/alpaca_eval
dataset
Repository for the paper's released code and data supporting the RealRank automatic LLM ranking analysis.
yale-nlp/RealRank
benchmark
CHEF is one of the three real-world datasets used to evaluate STEEL.
THU-BPM/CHEF
dataset
CrewAI is presented as a Python framework for defining LLM-based agents, tasks, tools, sequential execution, entity memory, and callbacks.
crewAIInc/crewAI
framework
Jupyter notebook implementing a workflow that performs root-cause analysis from a directly-follows graph abstraction and adds evaluation steps such as confidence scoring and reasoning output.
fit-alessandro-berti/agents-trial
implementation
Jupyter notebook implementing the process-mining fairness workflow with protected-group identification and comparison between protected and non-protected cases.
fit-alessandro-berti/agents-trial
implementation
Official Chronos repository for pretrained time-series forecasting models.
amazon-science/chronos-forecasting
implementation
Datadog Toto repository for Time-Series-Optimized Transformer for Observability.
DataDog/toto
implementation
Official Google Research TimesFM repository for the Time Series Foundation Model.
google-research/timesfm
implementation
IBM Granite TSFM TinyTimeMixer model implementation.
ibm-granite/granite-tsfm
implementation
MOMENT repository for a family of open time-series foundation models.
moment-timeseries-foundation-model/moment
implementation
TiRex repository for zero-shot forecasting across long and short horizons.
NX-AI/tirex
implementation
Moirai/Uni2TS repository for universal time-series forecasting Transformers.
SalesforceAIResearch/uni2ts
implementation
Sundial repository for highly capable time-series foundation models.
thuml/Sundial
implementation
Lag-Llama repository for probabilistic time-series foundation forecasting.
time-series-foundation-models/lag-llama
implementation
Repository for the Re4 Scientific Computing Agent, including source code in Jupyter Notebook and Python script formats and a README describing the rewriting-resolution-review-revision logical chain.
ChengAo21/Re4_Sci_Agent
framework
Repository for the ICLR 2023 ReAct prompting paper, including data, prompts, HotpotQA, FEVER, ALFWorld, and WebShop notebooks, plus Wikipedia environment wrappers.
ysymyth/ReAct
benchmark
Repository for the paper's training-data synthesis implementation.
BAAI-DCAI/Training-Data-Synthesis
implementation
GitHub repository associated with the REAL websites, framework, and leaderboard for benchmarking autonomous web agents.
agi-inc/agisdk
framework
Repository containing the paper's complete demonstration code and challenge materials and referenced as the Sim-to-Real repository.
AMD-AIM/Physical_AI_Challenge
Workshop implementation associated with the synthetic-data-generation and Sim-to-Real manipulation workflow.
PhysicalAI-AIM/Robot_synthetic_data_generation_workshop
Open-source real-time Vulkan 3D Gaussian Splatting renderer/plugin used to implement the reconstruction-to-simulation bridge described by the Real2Sim pipeline.
ZJLi2013/vk-gsplat-plugin
Google Research code for REALM pre-training, document-index refreshing, example generation, released checkpoints, and integration with the ORQA fine-tuning code.
google-research/language
implementation
Repository containing the yield-farming simulation environment used for strategy analysis.
xujiahuayz/yieldAggregators
implementation
Official code repository for reproducing the paper's Game of 24, ALFWorld, BlocksWorld, and Tic-Tac-Toe experiments.
agentification/RAFA_code
Official implementation and release repository for the DramaSR-LRM pipeline, benchmark data structure, training, inference, evaluation, and model checkpoints.
198808xc/DramaSR-LRM
benchmark
GitHub directory containing REVEAL code, AIGC-text-bank files, configurations, inference scripts, training scripts, and setup instructions.
microsoft/AnthropomorphicIntelligence
dataset
Official repository maintained by the authors to collect and update literature and resources on static and dynamic LLM benchmarking under data contamination.
SeekingDream/Static-to-Dynamic-LLMEval
The ParlAI repository contains the framework, tasks, model access, fine-tuning and evaluation code used to reproduce and extend the paper's chatbot recipes.
facebookresearch/ParlAI
Repository released by the authors for ReCode, including the framework and associated research artifacts.
ZJU-CTAG/ReCode
dataset
Microsoft's RecAI research repository contains the InteRecAgent implementation in a dedicated subdirectory and describes the paper's LLM-as-brain/recommender-models-as-tools system.
microsoft/RecAI
Official repository accompanying the paper, with scripts for threshold sensitivity, context, typo, adversarial-prompt, and long-form experiments.
duygunuryldz/uncertainty_in_the_wild
GitHub repository for the benchmark code and evaluation tooling introduced by the paper.
JiseungHong/ReCUBE
benchmark
Repository released by the authors for LLM-Rsum, with code paths for ChatGPT/Llama experiments, recursive memory, retrieval, MemoChat, and MemoryBank comparisons.
qingyue2014/Rsum
Official repository for the paper, containing Red-Eval prompt/evaluation code, harmful-question resources, result files, and Starling safety-alignment training code.
declare-lab/red-instruct
Code and data repository for the RedAgent framework, including context probing, memory, adaptive routing, evaluation, and example workflows.
QuirkShark/RedAgent
Repository for the RedKnot serving runtime, including the head-aware KV-reuse, Elastic Sparsity, SegPagedAttention, model-adapter, and benchmark implementation.
rednote-machine-learning/RedKnot
Repository containing code for preparing the RedPajama datasets and reproducing the data-processing workflow described by the paper.
togethercomputer/RedPajama-Data
dataset
HuggingFace Diffusers repository, used for refactoring diffusion-model implementation files such as UNet and scheduler sources.
huggingface/diffusers
Official repository released by the authors with implementations, demos, prompts, and research artifacts for Reflexion experiments.
noahshinn024/reflexion
Repository containing the implementation associated with the regime-aware continual adaptive portfolio-management framework.
Dumail/ReCAP
framework
Repository associated with the paper's Qwen2.5-0.5B SFT, DPO, RLOO, reward-model, Countdown, and external-verifier experiments.
Yifu93/LLM-Reinforcement-Learning
implementation
Code repository for the Relational Representation Distillation implementation reported by the paper.
giakoumoglou/distillers
implementation
Public source code for the paper's RPS-based ordinal conformal prediction method and experiments.
stefanahaas41/rps-ordinal-conformal-prediction
Repository maintaining extended notes, open research items, and per-claim literature verdicts for the removable-defects project.
macrokit/removable-defects
The Arena Hard repository is used as the pairwise chatbot evaluation setup; the authors generated additional model outputs and scored them with the compared judges.
lm-sys/arena-hard
benchmark
The public implementation of RepoAgent, an LLM-powered repository agent for generating, maintaining, updating, and understanding repository-level documentation.
OpenBMB/RepoAgent
framework
Official RepoBench repository containing data, evaluation scripts, experiment code, and documentation for the benchmark introduced by the paper.
Leolty/repobench
dataset
Repository containing RepoGraph code for constructing and retrieving repository graph context, plus integrations with Agentless and SWE-agent and scripts for SWE-bench evaluation.
ozyyshr/RepoGraph
framework
RepoReviewer repository containing the Python backend, Next.js frontend, screenshots, CLI/API/web workflow, and templates or utilities for future empirical evaluation and annotation.
peng1z/RepoReviewer
framework
Official codebase for training ReProbe/UHead-style verifiers, generating annotated reasoning datasets, evaluating ReProbe and baselines, and reproducing benchmark tables.
ReProbe/ReProbe
benchmark
GitHub repository containing data from the paper's experiments, provided to support reproducibility of the proposed evaluation approach.
andstor/agentic-ai-eval-replication-package
implementation
Code repository for the paper's deep-search reranking and Effective Token Cost experiments.
sahel-sh/DeepHone
Official code release with command-line tools, prompts, metrics, validation utilities, tests, and a small smoke-test split for the three ResearchBench tasks.
ankitala/ResearchBench
benchmark
Official repository for the paper, containing throughput and length experiments, negative-sample analysis, predictor tools, serving integrations, environment files, and cached results.
LLMkvsys/rethink-kv-compression
Repository containing PopQA training and test data, preprocessing artifacts, generator and reranker LoRA adapters, training and testing scripts, prompt-generation code, and utilities.
CoderrrSong/CoRAG
dataset
Repository for Byzantine Fault Tolerance in LLM-Based Multi-Agent Systems, including pilot experiments, prompt-level confidence probing, hidden-level confidence probing, datasets, pretrained confidence probes, and experiment scripts.
Z1ivan/Byzantine-Fault-Tolerance-in-LLM-MAS
framework
Official repository for the BAR-RAG training, filtering, inference, and evaluation pipeline introduced in the paper.
GasolSun36/BAR-RAG
The KILT repository provides the standardized Wikipedia knowledge source used for retrieval in both dialogue benchmarks.
facebookresearch/KILT
ParlAI is the dialogue research framework in which the paper trains and evaluates all models and through which the RAG-based implementations and pretrained models were released.
facebookresearch/ParlAI
A curated, continuously updated collection of retrieval-augmented generation work for computer vision, organized across visual understanding, generation, documents, video, multimodal tasks, and embodied AI.
zhengxuJosh/Awesome-RAG-Vision
Repository identified by the paper as containing the code used for the Polymer Literature Scholar and its RAG workflows.
Ramprasad-Group/RAG
The paper's RAG implementation and experiment scripts were ported to and open-sourced within the Hugging Face Transformers repository.
huggingface/transformers
Official companion repository for the survey, containing survey materials and an evolving RAG knowledge base covering papers, datasets, benchmarks, evaluation resources, and toolkits.
Tongji-KGLLM/RAG-Survey
Official codebase for RetroMAE pre-training and downstream dense-retrieval fine-tuning, with pretrained model resources referenced by the paper.
staoxiao/RetroMAE
Open-Finance-Lab repository for FinRL Contest 2024, linked directly in the paper alongside the contest website.
Open-Finance-Lab/FinRL_Contest_2024
framework
Official repository released by the authors with code, data, and agent-generated traces for reproducing the study.
ChuanMeng/text-ranking-in-deep-research
benchmark
Implementation repository used for the Rank1 reasoning-based re-ranker evaluated in the pipeline and query-mismatch experiments.
orionw/rank1
Repository for the BrowseComp-Plus fixed-corpus deep-research benchmark and its evaluation tooling.
texttron/BrowseComp-Plus
dataset
Official Qwen3 repository for the model family used in the paper's most controlled comparisons of scale, post-training, reasoning mode, dense versus MoE architecture, and quantization.
QwenLM/Qwen3
Repository containing the prompts and RL training code for the Ultimatum Game, matrix games, and DealOrNoDeal domains studied in the paper.
minaek/reward_design_with_llms
implementation
Repository for Stackelberg Reward Shaping (SRS) and its integration with inference-time alignment methods.
Haichuan23/Stackelberg-Reward-Shaping
implementation
Repository containing code and experiment folders for the rewarded-soups method, including LLaMA RLHF and image-captioning reproductions.
alexrame/rewardedsoups
Repository for reproducing or using RFEval, the paper's benchmark for auditing reasoning faithfulness under counterfactual reasoning intervention.
AIDASLab/RFEval
dataset
Repository containing the implementation and experiments for the risk-aware GUMDP framework and ERM-MCTS evaluation introduced in the paper.
gh0stwin/risk-aware-gumdp
GitHub repository for the simulator used to quantify uncertainty propagation in AI-augmented systems.
EMezzi/AI-Augmented
implementation
Official Risky-Bench repository containing benchmark datasets, data generation scripts, evaluator components, and evaluation workflows for the paper.
SophieZheng998/Risky-Bench
dataset
Repository released by the paper authors for RLAIF-V.
RLHF-V/RLAIF-V
Repository linked by the paper as the code artifact for Variational Alignment with Re-weighting; the repository page was empty when checked.
DuYooho/VAR
implementation
Repository for loading and manipulating RoboNet and for training the supervised inverse and video-prediction models used with the dataset.
SudeepDasari/RoboNet
Python implementation of C-EDL and the comparative experimental framework, including supported datasets, evidential models, abstention metrics, and adversarial attacks.
team-daniel/cedl
Repository containing prompts and templates used to instantiate LLM-Modulo for Travel Planner and Natural Plan domains.
Atharva-Gundawar/LLM-Modulo-prompts
framework
Repository containing the notebook and reproduction-oriented materials for the clean, noisy, and denoised taxi-fare comparison.
padmavathi026/Smart-Fare-Prediction
implementation
A project that crawls WeChat users' profile pictures with usernames and visualizes them; used as the source project for the bug-fixing task.
yangxuanxc/wechat_friends
Official ROSClaw repository implementing the physical-agent runtime, robot and tool integration, safety and simulation components, execution trace capture, resource management, and supporting documentation.
ros-claw/rosclaw
Repository for serving, training, and evaluating LLM routers, including router types corresponding to the paper such as matrix factorization, similarity-weighted ranking, BERT, causal LLM, and random routing.
lm-sys/routellm
framework
Repository released with the paper for adaptation, router-sensitivity scoring, structural pruning, and evaluation.
ianKa1/MoE_pruning
Official RouterBench code repository containing data converters, prompt embeddings, predictive and cascading routers, evaluation code, configurations, tests, and visualization utilities.
withmartian/routerbench
benchmark
Repository for the paper's RUArt implementation, including model code, configuration, inference entry points, dependency instructions, and links to pretrained and preprocessed files.
xiaojino/RUArt
Repository reported by the paper for the AtomicTranslation code used in the language-to-logic translation experiments.
KrisAesoey/AtomicTranslation
dataset
Repository containing the S-LoRA serving implementation, benchmark scripts, tests, and documentation for Unified Paging, heterogeneous LoRA batching, and the evaluated baselines.
S-LoRA/S-LoRA
GitHub repository for a convolutional neural stock-market technical analyser used as the starting point for the paper's proposed model.
philipxjm/Convolutional-Neural-Stock-Market-Technical-Analyser
implementation
Repository for SafeArena, a benchmark for assessing harmful capabilities and safety risks of autonomous web agents.
McGill-NLP/safearena
dataset
Repository containing code and prompts used when writing the paper, including agent setup notebooks, safety architecture notebooks, image-generation safety notebooks, requirements, utilities, and unsafe agent test requests.
ishaandomkundwar/Agent-Safety
dataset
Repository for the SafeRAG benchmark, including attack-task data/knowledge bases, retrievers, prompts, metrics, evaluators, model interfaces, and quick-start evaluation code.
IAAR-Shanghai/SafeRAG
dataset
Google Gemini full-stack LangGraph quickstart prototype used as the basis for a query-decomposition, search, reflection, and answer-finalisation scaffold.
google-gemini/gemini-fullstack-langgraph-quickstart
system
Repository for SafeSearch code, dataset, prompts, assets, and red-teaming configurations.
jianshuod/SafeSearch
dataset
Official implementation of the Vera safety-testing framework, including taxonomy exploration, case generation, adaptive execution, Vera-Bench, and guard-model fine-tuning components.
Yunhao-Feng/Vera
framework
DeepSpeed repository containing the distributed training framework and MoE functionality introduced and evaluated by the paper.
microsoft/DeepSpeed
framework
Repository containing PyTorch DiT model definitions, pretrained ImageNet checkpoints, and training and sampling code corresponding to the paper.
facebookresearch/DiT
Revised Tau2-Bench repository used by the authors because they describe the original benchmark as containing noisy data.
AGI-Eval-Official/tau2-bench-revised
benchmark
Public Flan-T5 checkpoints released with the paper in the T5X model repository.
google-research/t5x
Repository containing the MMLU chain-of-thought prompts used for the paper's MMLU evaluation.
jasonwei20/flan-2
Repository for BIG-bench, from which the paper evaluates 62 tasks covering reasoning, knowledge, social behaviour, and other language-model capabilities.
google/BIG-bench
benchmark
LLM-Random research codebase containing model-training infrastructure and research configurations associated with the fine-grained MoE scaling-law experiments.
llm-random/llm-random
implementation
BigSparse project code associated with the paper's sparsity experiments and scaling-law fitting workflow.
google-research/jaxpruner
NL2Flow is the automated workflow problem generation and symbolic evaluation framework used to generate planning problems, compile PDDL, and evaluate plans.
IBM/nl2flow
framework
NL2FLOW-Runner contains code for running the experiments reported in the paper.
IBM/nl2flow-runner
implementation
Repository containing BiomedGPT training, fine-tuning, preprocessing, dataset documentation, and model-use resources associated with the original and extended BiomedGPT research line.
taokz/BiomedGPT
implementation
Repository containing canonical tool contracts, interface condition renderers, validation and structured diagnostics, deterministic sandbox executors, run matrix harnesses, structured logging, and aggregate metric scripts.
akgitrepos/schema-first-tool-apis-experiments
benchmark
OpenHands CodeAct is used as one of the agent frameworks evaluated on ScienceAgentBench, alongside direct prompting and self-debug.
All-Hands-AI/OpenHands
framework
Repository containing code and data access instructions for ScienceAgentBench, including benchmark structure, agent/evaluation scripts, and links to benchmark materials.
OSU-NLP-Group/ScienceAgentBench
dataset
Repository for the Calo-VQ model used by SciFi to reproduce a calorimeter simulation inference and plotting pipeline.
qibin2020/calo-VQ
implementation
Repository containing implementation details for the SciFi autonomous agentic scientific workflow framework.
qibin2020/scifi
framework
Repository containing SciPredict data, configurations, evaluation scripts, background-knowledge pipelines, MCQ-to-free-form conversion, and experiment-running instructions.
scaleapi/scipredict
dataset
Official repository containing the SCIZOR curation code, customized Octo and RoboMimic training paths, and scripts for progress-based scoring and deduplication.
UT-Austin-RPL/SCIZOR
Hosts training and inference scripts, SeaBench-Audio materials, project assets, and links to the released model and benchmark.
DAMO-NLP-SG/SeaLLMs-Audio
benchmark
Open-source Search-R1 training and inference code for reasoning-and-search interleaved LLMs, including PPO/GRPO training and retrieval integration.
PeterGriffinJin/Search-R1
implementation
Repository for Reasoning-Reinforced Representation for Search, with release-status information and a linked model artifact.
ytgui/Search-R3
framework
Public repository containing the SecRepoBench implementation, benchmark metadata, descriptions, harnesses, tools, and scripts for running inference and evaluation.
ai-sec-lab/SecRepoBench
dataset
Repository released by the authors for RLHF technical artifacts, reward models, and PPO/PPO-max code.
OpenLMLab/MOSS-RLHF
implementation
C-Eval benchmark repository used to assess whether PPO alignment degrades Chinese language-understanding capabilities.
SJTU-LIT/ceval
benchmark
Provides training code, HH-RLHF data with preference-strength information, and the GPT-4-cleaned validation set.
OpenLMLab/MOSS-RLHF
dataset
Official code repository containing the implementation needed to reproduce the GazeReward framework and experiments.
Telefonica-Scientific-Research/gaze_reward
framework
Public implementation repository for Pythia, the modular hallucination-monitoring system evaluated and discussed in the paper.
wisecubeai/pythia
Repository containing code for data generation and risk-control experiments associated with selective conformal classification.
git4review/conformal_selective_classification
implementation
Repository linked from the paper's official project page; it contains MATRIX simulation source code, an example runner, requirements, and released MATRIX-generated alignment data.
ShuoTang123/MATRIX
implementation
Official repository for the paper's self-collaboration code-generation framework, containing generation/evaluation scripts, core code, data, and evaluation utilities.
YihongDong/Self-collaboration-Code-Generation
implementation
Repository location for the open-source UL2 model checkpoints used as one of the evaluated language models.
google-research/google-research
BIG-bench StrategyQA task repository used for the paper's question-only StrategyQA evaluation set.
google/BIG-bench
benchmark
Contains data-processing, SFT, iterative reward-model training and filtering, inference, GPT-4 evaluation, and PPO code for Self-Evolved Reward Learning.
microsoft/DKI_LLM
framework
Repository for Self-Evolving GPT; the README states that se_gpt_MAIN.py shows the main workflow of the framework.
ArrogantL/se_gpt
framework
Official code and data repository for generating Self-Instruct data, classifying tasks, generating instances, filtering and formatting data, fine-tuning GPT3, and evaluating on the released user-oriented tasks.
yizhongw/self-instruct
dataset
Repository dedicated to the paper's SKR experiments, with data, chain-of-thought results, and scripts for SKR_prompt, SKR_icl, SKR_cls, and SKR_knn.
THUNLP-MT/SKR
Official code repository for Self-Play Preference Optimization, including training, generation, ranking, and evaluation scripts and released model references.
uclaml/SPPO
Repository containing the original Self-RAG implementation, critic and generator data-creation workflows, retriever setup, training scripts, and short- and long-form evaluation code.
AkariAsai/self-rag
Official repository for the SELF-REFINE framework, containing code, prompts, data, task runners, evaluation scripts, and examples for the paper's studied tasks.
madaan/self-refine
Repository for AlpacaEval, the automatic instruction-following evaluation framework used for the paper's AlpacaEval 2.0 leaderboard evaluation.
tatsu-lab/alpaca_eval
benchmark
Official PyTorch codebase for the Image-based Joint-Embedding Predictive Architecture, including training code, masks, model definitions, configurations, checkpoints, and logs.
facebookresearch/ijepa
Repository for the SelfAI system, including its experiment-management software and implementation-oriented documentation.
XiaoXiao-Woo/SelfAI
Contains the paper's hybrid-retrieval defense, detection implementations, evaluation and experiment scripts, result files, sanitized examples, corpus setup instructions, figures, and reproducibility documentation.
scthornton/semantic-chameleon
system
Contains the pipeline for loading CoQA and TriviaQA, generating answers, clustering semantic similarities, computing likelihoods and uncertainty measures, evaluating AUROC, and reproducing the paper's analyses, together with the released hand-labelled semantic-equivalence data.
lorenzkuhn/semantic_uncertainty
dataset
TensorFlow lm_1b repository cited for the released CNN-BIG-LSTM model and training recipes from Jozefowicz et al. (2016).
tensorflow/models
implementation
Code repository linked by the paper for Sentence-BERT and sentence-transformer models.
UKPLab/sentence-transformers
The paper's released Sequence Tutor implementation within TensorFlow Magenta, including a checkpointed melody RNN.
tensorflow/magenta
Open-source Azure production trace repository used as an evaluation data source.
Azure/AzurePublicDataset
dataset
The repository implements an SGDE API and client for training, uploading, downloading, and using generative models, and includes a demonstration notebook and model examples.
archettialberto/SGDE
Code repository for the ShapG method introduced in the paper.
vectorsss/shapG
implementation
Self-service snack bar kiosk system repository containing requirements documentation, automated Robot Framework acceptance tests, C4 architecture documentation, ADRs, and traceability audit material.
JYU-GENIUS-project/snackbar_v1
implementation
First iteration for vibe coding in the study; implements a snack kiosk system using React, TypeScript, PostgreSQL, Node, and Express.
JYU-GENIUS-project/VibeCode1
implementation
Lovable-generated campus-treats prototype used as the unstructured vibe coding example.
Lovablekokeilu/campus-treats
implementation
Official codebase implementing the paper's Shifting Attention to Relevance uncertainty-estimation pipeline and dataset/model scripts.
jinhaoduan/SAR
implementation
Official PyTorch implementation of the Sim2Seg visual translator and RL training pipeline, with configurations, models, sample environments, and training instructions.
rll-research/sim2seg
Repository for SimCSE code and pretrained sentence-embedding models.
princeton-nlp/SimCSE
implementation
Official Microsoft implementation of SimMIM with training and fine-tuning code, configurations, and released pretrained/fine-tuned model resources.
microsoft/SimMIM
implementation
Open-source Python framework for building and orchestrating linear deterministic agentic workflows.
DevenPanchal/simpliflow
framework
Repository containing ready-made example workflows, workflow utilities, and usage material for simpliflow.
DevenPanchal/simpliflow-usage
Repository for the SimDist framework, including quadruped expert training, simulation data generation, world-model pretraining, deployment, real-world data processing, and finetuning.
CLeARoboticsLab/simdist
Jericho is presented as an open-source learning environment for human-authored interactive-narrative games.
microsoft/jericho
TextWorld is presented as a framework for procedural generation and experimentation in text-based games.
microsoft/textworld
Repository containing supplementary materials for the paper, organized into metrics, heatmaps, and equity-line outputs.
Maciej-13/spxw-options-sizing-paper-appendix
Official repository for the skfolio Python library, containing the implementation of the portfolio-optimization and risk-management framework described in arXiv:2507.04176.
skfolio/skfolio
framework
Official repository for the paper's SHROOM system experiments, including Data and Experiments directories.
Sharif-SLPL/SE-2024-Task-06-SHROOM
The repository is linked as the paper's website and contains project materials/figures for Small Language Models: Survey, Measurements, and Insights.
UbiquitousLearning/SLM_Survey
Official Natural Questions repository linked by the paper for the NQ-Open evaluation benchmark.
google-research-datasets/natural-questions
dataset
Repository containing SMART-LLM task-plan generation and execution scripts, robot definitions and skills, and the benchmark task data used for AI2-THOR evaluation.
SMARTlab-Purdue/SMART-LLM
dataset
Qwen3-Coder repository linked by the paper for the 30B open-weights code-generation model evaluated under NO-SPARK and WITH-SPARK conditions.
QwenLM/Qwen3-Coder
Repository for the Smoothie label-free LLM routing method.
HazyResearch/smoothie
implementation
Public Python implementation associated with the proposed social recommendation system.
BehafaridMjf/Social-Recommendation-System
implementation
Official Google Research directory containing self-contained prototype notebooks for the Socratic Models applications evaluated in the paper.
google-research/google-research
Repository containing recovery, relabeling, validation, environment, download, and reproduction scripts for LPQLD on ImageNet-1K and ImageNet-21K-P.
he-y/soft-label-pruning-quantization-for-dataset-distillation
Modular plug-in framework and CLI for composing target models, attacks, defenses, datasets, and judgers, with released evaluation records and experiment configurations.
datasec-lab/PromptSecurity
benchmark
Repository implementing the Sim2Reason scene-generation, simulation, QA-generation/filtering, RL training, checkpoint, and benchmark-evaluation workflow.
Sim2Reason/Sim2Reason
llama.cpp version 4501 is the execution backend for all experiments, and its llama-quantize tool produces the Q4_0 and Q4_K_M model variants.
ggerganov/llama.cpp
Repository for YOLOv8 traffic-density estimation, used as the basis of the Traffic Agent's vehicle detection and congestion-count pipeline.
FarzadNekouee/YOLOv8_Traffic_Density_Estimation
Repository for the YOLO11 Flare Guard real-time smoke and fire detector used by the Safety Agent.
sayedgamal99/Real-Time-Smoke-Fire-Detection-YOLO11
Repository containing social-task generation, conversation generation and processing, self-training/RL components, model deployment, automatic evaluation, human evaluation, plotting, and reproduction instructions.
sotopia-lab/sotopia-pi
Official SPA-Bench repository containing benchmark code, data, framework, model server, pipeline, documentation, and setup files.
ai-agents-2030/SPA-Bench
dataset
Official research repository for Sparse High Rank Adapters, including the paper summary and implementation references.
Qualcomm-AI-research/SHiRA
implementation
Repository associated with the Sparse Logit Sampling paper and Random Sampling KD method; at extraction time the README stated that code would be uploaded after company approvals.
akhilkedia/RandomSamplingKD
implementation
Repository released by the authors for the Sparsing Law study, including code and checkpoints.
thunlp/SparsingLaw
GitHub Spec Kit documentation for spec-driven development, including the staged specification, planning, and tasking workflow used as the conceptual and procedural base for Spec Kit Agents.
github/spec-kit
framework
Repository containing training and distillation scripts, BigBench Hard and mathematical-benchmark evaluation code, processed-data workflows, prompting notebooks, and notebooks for aligning code-davinci and FlanT5 tokenized outputs.
FranxYao/FlanT5-CoT-Specialization
implementation
GitHub repository associated with the SPEECH method and released resources.
zjunlp/SPEECH
dataset
A curated repository associated with the paper that organizes efficient architecture papers according to the survey's categories.
weigao266/Awesome-Efficient-Arch
Repository for the Semantic Pyramid Indexing FAISS/Qdrant plug-in introduced and evaluated by the paper.
FastLM/SPI_VecDB
framework
Official code repository for SSAST, including self-supervised pretraining, downstream fine-tuning recipes, SUPERB integration, and released pretrained models.
YuanGongND/ssast
Mesh TensorFlow MoE implementation cited by the paper as code for its models.
tensorflow/mesh
implementation
Repository for StableToolBench, the paper's stability-oriented benchmark built on ToolBench.
THUNLP-MT/StableToolBench
benchmark
Repository released by the authors containing data-making scripts, training code, safety and reasoning benchmark code, and overrefusal-ablation utilities.
UCSC-VLAA/STAR-1
Repository explicitly linked by the paper for Star-Agents code. At extraction time, the public repository contains a README stating that the code will be coming soon rather than a released implementation.
CANGLETIAN/Star-Agents
Official STaRK repository containing benchmark loading utilities, preprocessing code, embeddings helpers, evaluation scripts, configuration, and documentation.
snap-stanford/STaRK
dataset
Official KernelBench repository used by the paper to benchmark runtime of PyTorch baselines and LLM-generated kernels.
ScalingIntelligence/KernelBench
dataset
Repository for the SciBORG manuscript, with setup instructions, framework usage examples, agent construction, and benchmarking guidance tied to the paper release.
chopralab/sciborg_manuscript_repo
framework
Directory containing SciBORG benchmark notebooks and trace notebooks corresponding to the supporting-information experiments.
chopralab/sciborg
benchmark
Repository reported by the paper as the source code for reproducing the pumped-storage DDQN state-representation study.
Fluxons/hydrodam
implementation
Repository containing the processed datasets, subject code, static-analysis implementation, machine-learning pipeline, scripts, outputs, feature selection, tuning, cross-validation, and SHAP analyses used in the paper.
imran9pk/replication-package_method_energy_java
Repository containing historical changes in S&P 500 constituents, used to restrict backtest positions to stocks that belonged to the index on each date.
fja05680/sp500
dataset
IMPROVER is an operational probabilistic weather forecast post-processing system used to bias-correct, calibrate, threshold, smooth, and blend forecast products.
metoppv/improver
implementation
Contains data-engineering utilities, synthetic-data generation, the three experimental training flows, SFT, DPO and DTFT configurations, and instructions for reproducing the final StatLLaMA path.
HuangDLab/StatLLaMA
implementation
Official repository for the Steve-Eye paper and project; it contains the project README, paper material, benchmark-result tables, and is linked from the authors' project website.
BAAI-Agents/Steve-Eye
benchmark
Repository for the BESSTIE sentiment and sarcasm classification benchmark for varieties of English.
unswnlp/BESSTIE
dataset
Repository for the InstruSum instruction-controllable summarization dataset referenced and used as an evaluation target in the paper.
yale-nlp/InstruSum
dataset
Repository indicated by the paper as containing all code and supplementary materials used for the SV-LSTM hybrid model study.
aperekhodko/sv_lstm_hybrid_model
implementation
Repository linked by the authors as the location of the curated dataset used for the stock movement and volatility prediction experiments.
hao1zhao/Bigdata23
dataset
Repository titled MSGCA: Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism, containing code and data folders for the proposed framework.
changzong/MSGCA
dataset
Repository containing code, configuration files, data-preparation scripts, pretraining routines, and trading scripts for STORM.
DVampire/Storm
framework
Official repository for the StoryScope pipeline, configuration, feature taxonomy, development stories, feature assignments, trained XGBoost models, and reproduction scripts.
jenna-russell/storyscope
dataset
Official ECCV 2026 release containing StoryAD-QA annotations, answer keys, evaluation code, and generation and answering prompts; it does not redistribute copyrighted movie media.
SEE-AI-Lab/ECCV2026_StoryTeller_StoryAD_QA
Code repository for the LLM-agent Cournot competition simulations and experimental workflow.
smojha/collusive-llm-agents
implementation
The referenced Llama 3 model card is associated with Llama-3-8B-Instruct, one of the local open-source models used in the ranking task.
meta-llama/llama3
Code released for the paper, including modular segmentation-attention and syntactic-attention layers and training scripts for translation, question answering, and natural language inference.
harvardnlp/struct-attn
Searchat is a local-first semantic search system for AI coding-agent conversations, supporting verbatim, distilled, and cross-layer retrieval over agent transcript histories.
Process-Point-Technologies-Corporation/searchat
framework
Open-source AI hedge fund project whose structured-summary prompt template, JSON action schema, and next-open execution conventions are adapted for the paper's LLM trading-agent backtests.
virattt/ai-hedge-fund
framework
Public reference implementation of Context-Aware Decoding, the decoding method adapted by FinCAD for parametric look-ahead-bias mitigation.
xhan77/context-aware-decoding
implementation
The public repository used to collect and release the Natural Instructions/Super-NaturalInstructions tasks and to provide official cross-task benchmark splits and experiment code.
allenai/natural-instructions
dataset
Open-source SuperHF training code, reward-model training code, PPO-RLHF baselines, experiments, evaluations, and chart-generation resources.
openfeedback/superhf
implementation
Google Research TensorFlow implementation of the SupCon method.
google-research/google-research
PyTorch implementation of Supervised Contrastive Learning and SimCLR-style training.
HobbitLong/SupContrast
Repository for the code used in the paper, with directories for the rate, prepare, assess, and pipeline stages.
COMSYS/artifact-evaluation-llm-support
system
Contains benchmark evaluation code, inference utilities, prompts, training code, and links to SURDS/SURDS_eval data used to reproduce the paper's evaluation and post-training workflow.
XiandaGuo/Drive-MLLM
Companion repository that organizes works on LLM-agent evaluation according to the survey's structure and tracks papers, benchmarks, methodologies, and frameworks.
Asaf-Yehudai/LLM-Agent-Evaluation-Survey
Framework for evaluating and optimizing agents and models in container environments, discussed as part of emerging standardized cross-environment agent evaluation.
harbor-framework/harbor
framework
LangChain AgentEvals package for evaluating agent trajectories, including trajectory matching and graph-based evaluation.
langchain-ai/agentevals
framework
HAL harness for centralized and reproducible evaluation across agent benchmarks.
princeton-pli/hal-harness
Repository for SWE-agent, the LM-based agent system that attempts to fix GitHub issues using an agent-computer interface and configurable tools.
SWE-agent/SWE-agent
framework
Repository containing SWE-Bench-CL data, dataset construction scripts, naive and agentic evaluation procedures, and LangGraph/FAISS-based continual-learning agent implementations.
thomasjoshi/agents-never-forget
dataset
Official SWE-bench repository containing benchmark tooling and resources for evaluating language models on real-world GitHub software-engineering issues.
SWE-bench/SWE-bench
dataset
Repository linked by the paper for the SWE-CI benchmark, associated code, and evaluation resources.
SKYLENAGE-AI/SWE-CI
dataset
Repository for the SWE-EVO benchmark, including benchmark materials and evaluation support for coding agents in long-horizon software evolution scenarios.
SWE-EVO/SWE-EVO
dataset
Official repository released for the SWE-Lancer benchmark, public Diamond split, code, and evaluation environment.
openai/SWELancer-Benchmark
dataset
Repository for SWE-QA-Pro, including evaluation materials for direct and agent modes and links to the paper and benchmark release.
TIGER-AI-Lab/SWE-QA-Pro
dataset
Repository containing the open-sourced inference implementation for serving SwiftKV-transformed models.
snowflakedb/arcticinference
Repository containing the open-sourced training and distillation implementation used to adapt models for SwiftKV.
snowflakedb/arctictraining
The paper states that JAX code for Switch Transformer and all model checkpoints are available in T5X.
google-research/t5x
implementation
The paper points to the Mesh TensorFlow MoE implementation as TensorFlow code for Switch Transformer.
tensorflow/mesh
implementation
Official inference repository for FLUX.1 models, including FLUX.1-dev and inpainting/editing variants.
black-forest-labs/flux
Repository containing experiment code for SynthSAEBench SAE architecture evaluations.
decoderesearch/synth-sae-bench-experiments
benchmark
Official repository for the T-Eval evaluation harness, benchmark protocols, test scripts, data access, and model-evaluation workflow.
open-compass/T-Eval
dataset
Codebase provided by the authors for reproducing TABCF experiments.
Panagiotou/TABCF
implementation
The paper states that this repository contains the reproducibility code for the benchmark of tabular classification methods.
machinelearningnuremberg/TabularStudy
benchmark
Repository containing the TAGAL implementations, prompt templates, dataset loaders, competitor implementations, generated examples, evaluation outputs, logs, and table-generation sources.
bronval/TAGAL-Tabular-Data-Generation-with-LLMs
implementation
Official TaskBench code and dataset directory within the Microsoft JARVIS repository.
microsoft/JARVIS
dataset
A JSON file encoding TDD principles as governance objects with bibliographic grounding, human-oriented intent, AI-native interpretation, operational constraints, and anti-patterns.
shahbazsiddeeq/TDD-manifesto
implementation
Repository linked by the paper for data and code supporting Self-Critique Fine-Tuning and Reinforcement Learning with Effective Reflection Rewards.
wanghanbinpanda/SCFT
Open-source Python framework extending SMAC with meta-learning and ensemble learning for pipeline automation.
automl/auto-sklearn
framework
Open-source Python implementation of sequential model-based algorithm configuration for hyperparameter optimization.
automl/SMAC3
framework
Open-source Python Auto-Pipeline tool using genetic programming to optimize tree-structured machine learning pipelines.
EpistasisLab/tpot
framework
Open-source Python framework for automated feature generation from relational datasets.
Featuretools/featuretools
framework
Open-source Python tool for hyperparameter optimization.
hyperopt/hyperopt
framework
Open-source Keras-based framework for searching deep network architectures using Bayesian optimization and network morphism.
keras-team/autokeras
framework
Microsoft open-source toolkit for neural architecture search and hyperparameter tuning across local or cloud execution environments.
microsoft/nni
framework
Open-source TensorFlow framework for automatically learning neural network architectures and ensembles.
tensorflow/adanet
framework
Repository released by the authors for the IN3 benchmark, Mistral-Interact training/inference code, interaction data, and evaluation scripts.
HBX-hbx/Mistral-Interact
dataset
Open LLaMA is the publicly available 13B model used in the paper's instruction-based fine-tuning experiments.
openlm-research/open_llama
implementation
Repository containing the TGN model, modules, data preprocessing utilities, self-supervised link-prediction training, supervised dynamic node-classification training, baseline configurations, and ablation commands.
twitter-research/tgn
implementation
Official TemporalBench repository containing evaluation scripts, scoring code, model-evaluation examples, and links to the released dataset and leaderboard.
mu-cai/TemporalBench
benchmark
Repository for the TensorFlow.js framework introduced and described by the paper.
tensorflow/tfjs
Repository for Tevatron; the current project has evolved beyond the original release and documents access to the v1 branch for original Tevatron features.
texttron/tevatron
Repository containing TextAtari agent/environment code, translators from Gym-style environments to natural language, prompt/decider modules, manuals, language trajectories, and visualization assets.
Lww007/Text-Atari-Agents
system
Python implementation of the three-stage TextReg pipeline, including RuleBank, gradient purification, semantic edit regularization, the guided optimizer, example execution scripts, and paper-aligned metrics.
luchengfu6/TextReg
framework
Repository accompanying the paper, with runnable TEP pipelines, configurations, benchmark support, and implementation code for deep compound AI system optimization.
MinghuiChen43/TEP
framework
Repository for the QA-FEEDBACK, Longformer reward-model, and T5/PPO experimental workflow used to study the reward-model accuracy paradox.
EIT-NLP/AccuracyParadox-RLHF
implementation
Repository associated with the AI Cosmologist paper, described by the paper as containing code and experimental data and by the repository README as containing configuration files, examples, and best AI-generated code for the Galaxy Zoo and Quijote demonstrations.
adammoss/aicosmologist
system
Contains the three generated submissions and associated experiment, review, and audit materials for compositional regularization, label noise and calibration, and pest detection.
SakanaAI/AI-Scientist-ICLR2025-Workshop-Experiment
Contains the template-free autonomous research pipeline, ideation and experimentation code, best-first tree-search configuration, prompts, launch scripts, and implementation documentation.
SakanaAI/AI-Scientist-v2
Repository providing the ICLR 2022 OpenReview data used to evaluate the automated reviewer.
fedebotu/ICLR22-OpenReviewData
Official repository for The AI Scientist framework, prompts, code templates, generated papers, run files, logs, and automated-review implementation.
SakanaAI/AI-Scientist
Repository linked by the paper for LLM uncertainty decomposition, with folders and scripts related to input uncertainty, decoding uncertainty, model uncertainty, data, models, utilities, and uncertainty scoring.
aditya-taparia/LLM-Uncertainty
implementation
Repository released by the authors for the agent-to-agent negotiation and transaction benchmark code and data.
ShenzheZhu/A2A-NT
benchmark
Official BRAVO challenge repository containing the evaluation toolkit, baselines, submission encoding utilities, benchmark instructions, dataset access information, and challenge results.
valeoai/bravo_challenge
benchmark
ParlAI project directory containing the CRINGE loss implementation and iterative-training support code, including cringe_loss.py, teachers.py, and safety_filter_world_logs.py.
facebookresearch/ParlAI
Official repository for the paper, containing generation code, data-formatting utilities, metric-related files, and the Mechanical Turk template used in evaluation.
ari-holtzman/degen
Meta Research repository associated with the paper's MAE?WSP pre-pretraining approach.
facebookresearch/maws
implementation
Code repository for the paper's controlled assessment pipeline, mitigation strategies, and fidelity-resistance evaluation.
ASTRAL-Group/BDC-mitigation-assessment
Repository containing scripts and pre-computed experimental results for the paper's probing, automatic expert labeling, trigger-target attribution, clustering, specialization analysis, and figure reproduction.
jerryy33/MoE_analysis
Code repository linked by the paper for the controlled case studies evaluating attribution methods under the two constructed scenarios.
AmTuTi1999/FMIBAMGTSE
Datatrove is the large-scale data-processing library used to build FineWeb; the paper links a FineWeb reproduction script in this repository.
huggingface/datatrove
Official repository for Calibration-Aware On-Policy Distillation, the method introduced and evaluated by the paper.
SalesforceAIResearch/CaOPD
implementation
Public implementation of Progressive Transformers retrained and evaluated to provide a BLEU reference scale.
BenSaunders27/ProgressiveTransformersSLP
Implementation repository for the sign-pose VAE variants introduced and evaluated in the paper.
GFaure9/SignPoseVAE
implementation
Public implementation of Sign-IDD retrained and evaluated as a non-latent diffusion reference baseline.
NaVi-start/Sign-IDD
Repository containing the paper's transparency materials, including SP-1 AI-usage summary, SP-2 navigation index, SP-3 documentation-adequacy account, SP-4 process documentation, and SP-5 development records.
MicheleLoi/JPEP
implementation
A framework for training or evaluating agentic systems with reinforcement learning.
Agent-One-Lab/AgentFly
framework
A Microsoft framework listed as part of the agentic RL framework ecosystem.
microsoft/agent-lightning
framework
An open-source framework for scaling LLM reinforcement learning.
NovaSky-AI/SkyRL
framework
A repository for verifiable environments used in LLM reinforcement learning.
PrimeIntellect-ai/verifiers
framework
A benchmark for evaluating agents on real software engineering issues.
swe-bench/SWE-bench
benchmark
A framework for tool-use reinforcement learning with LLM agents.
TIGER-AI-Lab/verl-tool
framework
A web environment benchmark used to evaluate autonomous agents on browser tasks.
web-arena-x/webarena
benchmark
Repository for the paper's released data, including generated Code Llama outputs used to support follow-on work on ranking LLM code-generation candidates.
slp-rl/budget-realloc
dataset
Repository accompanying the paper, containing SPR task materials, generated research outputs, case studies for Agent Laboratory and The AI Scientist v2, and pitfall-detection code.
niharshah/AIScientistPitfalls
dataset
Open-source implementation of The AI Scientist-v2, one of the two AI scientist systems evaluated in the paper.
SakanaAI/AI-Scientist-v2
system
Open-source implementation of Agent Laboratory, one of the two AI scientist systems evaluated in the paper.
SamuelSchmidgall/AgentLaboratory
system
Official Google DeepMind repository containing NarrativeQA document metadata, Wikipedia summaries, question-answer pairs, and story-download/verification scripts.
google-deepmind/narrativeqa
dataset
Repository released by the authors for obtaining and preprocessing decaNLP datasets, training and evaluating models, reproducing experiments, and tracking decaScore progress.
salesforce/decaNLP
AI-Descartes combines symbolic regression with formal reasoning to evaluate whether candidate scientific formulas are derivable from background axioms.
IBM/AI-Descartes
AI-Hilbert integrates experimental data and polynomial background axioms during candidate-law generation and can output exact or approximate derivability certificates.
IBM/AI-Hilbert
Official repository releasing generated stories and the crowdworker and in-house human-evaluation results used by the paper.
ZhuohanX/TheNextChapter
NeuralMagic MLPerf Inference v2.1 submission referenced by the paper for the compressed BERTLARGE and MobileBERT deployment results.
neuralmagic/mlperf_inference_results_v2.1
SparseML research directory containing oBERT scripts, recipes, tutorials, checkpoints links, and the OBS pruning implementation used to reproduce paper results.
neuralmagic/sparseml
Meta Llama Guard 2 model-card repository path for the safeguard model used to classify whether generated outputs violate predefined safety categories.
meta-llama/PurpleLlama
implementation
Official Google Research codebase for reproducing the paper's prompt-tuning experiments, with training configurations, released prompts, and T5.1.1 LM-adapted checkpoints.
google-research/prompt-tuning
T5 code, evaluation metrics, preprocessing routines, and checkpoint index used by the paper for its base models, data preparation, and reproducibility.
google-research/text-to-text-transfer-transformer
Resources and out-of-domain development data for the MRQA 2019 shared task used in the paper's zero-shot question-answering transfer experiments.
mrqa/MRQA-Shared-Task-2019
Repository containing the training, reward, evaluation, dataset-conversion, and inference code used for the paper's legal machine translation experiments.
aixiuxiuxiu/Legal-MT-SFT-RL
Repository associated with the Test-Driven AI Agent Definition paper, containing code or benchmark artifacts for compiling tool-using agents from behavioral specifications.
f-labs-io/tdad-paper-code
benchmark
GitHub Spec Kit is an open-source toolkit for specification-driven development using commands such as /speckit.constitution, /speckit.specify, /speckit.plan, /speckit.tasks, /speckit.analyze, and /speckit.implement.
github/spec-kit
framework
Official repository containing code and supporting materials for automated literature collection, deduplication, filtering, review assistance, and the paper's experiments.
trigaten/The_Prompt_Report
Companion code and artifact repository containing analysis scripts, prompt templates, query lists, judge labels, numerical result JSONs, probe configurations, leakage diagnostics, Procrustes tests, and steering analyses.
amanmehta-maniac/refusal-residue-release
Anthropic's official Skill-Creator used as one of the three meta-skill creators that generate treatment libraries from shared failure signals.
anthropics/skills
OpenAI/Codex official Skill-Creator used as one of the three meta-skill creators that generate treatment libraries from shared failure signals.
openai/skills
Sentient skill-creator repository corresponding to the harness-agnostic meta-skill creator written for the study.
sentient-agi/meta-skill-creator
A GitHub repository collecting papers related to LLM-based agents, linked by the survey as a related-papers resource.
WooooDyy/LLM-Agent-Paper-List
Public repository for the AIDev dataset, schema/CSV files, replication materials, and example notebooks supporting analyses of autonomous coding agents in GitHub PR workflows.
SAILResearch/AI_Teammates_in_SE3
dataset
Repository containing SHS source code, documentation, examples, test cases, anonymized participant responses, data dictionary, R and Python analysis scripts, questionnaires, and study protocol materials.
human-centered-ai-lab/system-hallucination-scale
Repository linked by the paper for the reproduction work associated with the study.
AIReproducibility2018
implementation
Repository containing released evaluation experiments and artifacts for baseline agents and model configurations on TheAgentCompany.
TheAgentCompany/experiments
Repository for the TheAgentCompany benchmark environment, tasks, data, and evaluation infrastructure introduced by the paper.
TheAgentCompany/TheAgentCompany
dataset
Repository implementing the Theorem-of-Thought multi-agent reasoning pipeline, including baselines, data, and the core ToTh code.
KurbanIntelligenceLab/theorem-of-thought
Repository containing the paper's multi-LLM collaboration and ToM reference implementation, including the gym-dragon environment and scripts for LLM-agent experiments.
romanlee6/multi_LLM_comm
Official code repository for DT-Mem, including training and fine-tuning code for the memory-augmented Decision Transformer.
luciferkonn/DT_Mem
A project associated with the survey's core-competency test framework for LLM evaluation.
HITSCIR-DT-Code/Core-Competency-Test-for-the-Evaluation-of-LLMs
dataset
Repository for the TileMix implementation introduced and evaluated by the paper.
HanzhiZhang-Ulrica/TileMix
Repository containing the DeepFund code used to implement the live fund-investment benchmark, agent workflow, prompts, and evaluation system.
HKUSTDial/DeepFund
system
The official Time-MoE repository associated with the paper's architecture and released resources.
Time-MoE/Time-MoE
dataset
Repository containing the TimeArena environment, resources, evaluation scripts, metric code, prompts, and oracle-calculation code used to run the benchmark.
ykzhang721/TimeArena
benchmark
Repository for the TimeBlind benchmark with setup instructions, data format, evaluation code, and metric implementation.
Baiqi-Li/TimeBlind
dataset
Repository containing code, data-processing materials, experiment scripts, results, and plotting notebooks for reproducing the paper's analyses.
felipemaiapolo/efficbench
implementation
Repository containing the tinyBenchmarks Python package, demos, tutorials, and links to tiny datasets for estimating LLM performance from curated small benchmark subsets.
felipemaiapolo/tinyBenchmarks
package
Official repository for the TLOB paper, including code folders for models, preprocessing, data handling, configuration, training scripts, requirements, and backtesting script.
LeonardoBerti00/TLOB
benchmark
Official repository containing TofuEval development/test identifiers and released annotations for factual consistency, written explanations, hallucination types, completeness key points, and topic categorization.
amazon-science/tofueval
dataset
Repository implementing TokUR's low-rank Bayesian weight perturbation, uncertainty evaluation, dataset preparation, and test-time-scaling experiments.
Wang-ML-Lab/TokUR
BMTools integrates the paper's evaluated tools and provides an open-source platform for extending foundation models with APIs and for building and sharing tool plugins.
OpenBMB/BMTools
dataset
Repository for ToolRoCo, a multi-turn tool-using LLM benchmark for collaborative robotic tasks with Cabinet, PackGrocery, and Sort tasks and four cooperation paradigms.
ColaZhang22/Tool-Roco
benchmark
Official repository containing the ToolAlpaca data, prompts, multi-agent generation code, training scripts, evaluation code, and recorded evaluation outputs.
tangqiaoyu/ToolAlpaca
dataset
Hosts the ToolCAD project website and paper-facing artifact page.
gongyifeiisme/toolcad-project
system
Repository currently titled Ziqiao-git/C-World but with README content for ToolGym. It describes ToolGym as an open-world tool-using environment built on 5,571 tools across 204 applications and includes code folders for task creation, tool retrieval, state controller, runtime, and evaluation.
Ziqiao-git/C-World
dataset
Repository for ToolBench/ToolLLM artifacts, including code, trained models, and demo released by the authors.
OpenBMB/ToolBench
dataset
Repository for the ToolMisuseBench benchmark implementation, generator, evaluator, and experiment reproduction workflow.
akgitrepos/toolmisusebench
benchmark
Repository for ToolPRMBench, the benchmark and associated code/data for evaluating process reward models in tool-using agents.
David-Li0406/ToolPRMBench
dataset
Detectron2 is listed among object detection and image segmentation models/frameworks in the TorchTraceAP application table.
facebookresearch/detectron2
framework
PyTorch Holistic Trace Analysis package referenced as the source of profiling metrics and rule-based trace-event runtime outlier analysis.
facebookresearch/HolisticTraceAnalysis
package
Repository containing the Touchdown corpus splits, graph files, navigation/SDR data structures, helper code, and license information.
lil-lab/touchdown
dataset
Open-source implementation of Self-Supervised Contrastive Pre-Training for Time Series via Time-Frequency Consistency.
mims-harvard/TFC-pretraining
implementation
GitHub repository for the Light Aircraft Game benchmark, which the paper includes as an application simulator in its benchmark characterization table.
liuqh16/CloseAirCombat
benchmark
The BosqueLanguage GitHub organisation is identified by the paper as the public location for experimental versions of the AISE-related systems, including the Bosque ecosystem components discussed in the paper.
BosqueLanguage
framework
Repository containing the implementation, experiment configurations, synthetic-ring generation procedure, and supporting evaluation artifacts for the auditable fraud-detection and agentic-investigation pipeline studied in the paper.
rahil1303/auditable-fraud-investigation
Repository containing X-FM code and pre-trained models.
zhangxinsong-nlp/XFM
implementation
Repository containing code for survival-model calibration methods including CiPOT and CSD-style calibration, plus experiment reproduction resources.
shi-ang/MakeSurvivalCalibratedAgain
implementation
A GitHub repository linked by the paper/project page that curates efficient-agent papers and resources corresponding to the survey taxonomy.
yxf203/Awesome-Efficient-Agents
Repository linked by the paper for code supporting its synthetic-GMM simulation and KL-divergence analysis.
ZyGan1999/Towards-a-Theoretical-Understanding-of-Synthetic-Data-in-LLM-Post-Training
Repository containing prompts and queries used in the experiments for the LLM-powered security alert investigation workflow.
Rub3cula/CyberHunt2025
system
A maintained collection of papers, methods, benchmarks, and resources associated with RAG-reasoning and agentic deep-research systems.
DavidZWZ/Awesome-RAG-Reasoning
Apollo is an open autonomous driving platform used as the representative automated-driving system context for the safety-requirements derivation task.
ApolloAuto/apollo
system
Official repository for the TAT-DQA dataset and benchmark introduced by the paper.
NExTplusplus/TAT-DQA
dataset
Repository containing processed evaluation datasets and code for WPQ, Local Order Quiz, Token Overlap, Canonical Order, and Min-K% experiments.
vsamuel2003/data-contamination
Repository for the ACL 2026 survey that records system-aware, serving-time, KV-centric optimization papers and organizes them using the paper's temporal, spatial, and structural taxonomy.
jjiantong/Awesome-KV-Cache-Optimization
Code repository implementing the paper's unified MoE compression framework and proposed Expert Trimming methods.
CASE-Lab-UMD/Unified-MoE-Compression
framework
ROS framework for embodied intelligence applications using robot API configuration and LLM calls.
Auromix/ROS-LLM
framework
ROS 2 command-line interface extension with LLM support.
fujitatomoya/ros2ai
system
Stretch AI system orchestrating skills for language-directed mobile manipulation.
hello-robot/stretch_ai
implementation
MCP server connecting AI assistants to installed ROS 2 applications and system operations.
lpigeon/ros-mcp-server
implementation
Project integrating llama.cpp with ROS 2 to enable LLM inference.
mgonzs13/llama_ros
implementation
Tool using LLMs to generate ROS codebases from high-level descriptions.
RoboCoachTechnologies/ROScribe
system
ROS/ROS2 MCP server enabling natural-language commands and monitoring of robot states and sensor data.
robotmcp/ros-mcp-server
ROS-MCP project included among the paper's representative ROS/MCP integrations.
Yutarop/ros-mcp
implementation
Repository containing the implemented prototype, generated code, and execution traces for the LLM workflow generation experiments.
dos-group/LLMWorkflowGenerator
system
Repository linked by the authors as the paper list for the survey on reasoning in large language models.
jeffhj/LM-reasoning
Haystack is the framework used to implement the paper's RAG workload with retrieval and question-answering pipeline behavior.
deepset-ai/haystack
framework
GitHub repository stated by the paper as the available source code for the multimodal financial forecasting work.
sarthak-12/thesis-dsaa
framework
Repository containing TraceCoder source code, position-key implementation, relational storage and viewer components, experiment problems, run scripts, and result artifacts.
devfitcs/TraceCoder
DeepMarket is the official open-source Python framework for LOB market simulation with deep learning. It contains TRADES and CGAN implementations/checkpoints, ABIDES-based simulation components, evaluation utilities, and the TRADES-LOB synthetic dataset.
LeonardoBerti00/DeepMarket
dataset
Repository for TradeTrap, the paper's system-level stress-testing framework for LLM-based autonomous trading agents.
Yanlewen/TradeTrap
framework
Repository for TradingAgents, the multi-agent LLM financial trading framework introduced and evaluated in the paper.
TauricResearch/TradingAgents
framework
Code repository for the LoRAM and QLoRAM training, recovery, alignment, and evaluation workflow introduced by the paper.
junzhang-zj/LoRAM
Repository associated with the paper's helpfulness preference data for training and evaluating helpful and harmless assistants.
anthropics/hh-rlhf
dataset
Repository for BIG-bench, one of the principal benchmark suites used to compare Chinchilla with Gopher across diverse language-model capabilities.
google/BIG-bench
benchmark
Original research code for DDPO and the RWR baselines used for the paper's diffusion reinforcement-learning experiments.
jannerm/ddpo
Official PyTorch implementation of DDPO with GPU and LoRA support, linked as an update from the paper's project page.
kvablack/ddpo-pytorch
implementation
Repository containing released model samples for sampling-based NLP evaluations reported in the paper.
openai/following-instructions-human-feedback
Repository containing reference code for ILF experiments, refinement scoring, reward models, evaluation scripts, and links to the released SLF5K and finetuning datasets; the authors note that excluded data-generation and cleaning steps mean it is not a ready-to-run reproduction package.
JeremyAlain/imitation_learning_from_language_feedback
implementation
Contains Sandbox social-simulation code, released interaction data, Stable Alignment training code, and links to released socially aligned model checkpoints.
agi-templar/Stable-Alignment
Repository accompanying the paper's representation-based cut-statistic training-subset selector and experimental pipeline.
hunterlang/weaksup-subset-selection
Repository containing GSM8K train/test data, calculation annotations, example model solutions, and illustrative calculator/model code.
openai/grade-school-math
dataset
Repository for the TEAL method and sparse inference implementation introduced in the paper.
FasterDecoding/TEAL
implementation
Repository for TRAJECT-Bench, including public data, tool definitions, query generation materials, and evaluation scripts for model and ReAct-style agentic tool-use evaluation.
PengfeiHePower/TRAJECT-Bench
dataset
GitHub data source cited for the Stochastic Block Model dynamic graph benchmark used in the experiments.
IBM/EvolveGCN
dataset
Official ROLAND repository used by the authors to run the ROLAND baseline five times for MAP/MRR comparison.
snap-stanford/roland
implementation
Author-provided code repository for the experiments validating the theoretical critical-point structures of trained linear transformers.
chengxiang/LinearTransformer
Repository containing Python code, prompt files, forex price data, annotated sentiment data, prediction files, and scripts for reproducing prompt runs and comparative results.
giorgosfatouros/Financial-Sentiment-Analysis-with-ChatGPT
dataset
Repository released by the authors containing code, generated translations, and human quality assessments for the quality-aware cascaded translation system.
deep-spin/translate-smart
implementation
Official repository for TravelPlanner containing agent runners, database assets, tools, postprocessing, evaluation scripts, and benchmark usage instructions.
OSU-NLP-Group/TravelPlanner
benchmark
Official implementation and experiment code for the Treble Counterfactual VLM intervention and its POPE and MMHal-Bench evaluations.
TREE985/Treble-Counterfactual-VLMs
Repository containing Tree of Thoughts code, task implementations, prompts, and logged experimental trajectories.
princeton-nlp/tree-of-thought-llm
framework
Official CAGE Challenge 4 repository for the multi-agent cyber-defense environment used as one of Trident's two main training and evaluation testbeds.
cage-challenge/cage-challenge-4
Official CyberWheel repository for the autonomous cyber-defense simulation environment used to train and evaluate Trident's adaptive red agent.
ORNL/cyberwheel
Official AG2 example repository from which the paper draws four representative MAS applications for case-study evaluation.
ag2ai/build-with-ag2
Open-source implementation repository for the TrinityGuard framework introduced by the paper.
AI45Lab/TrinityGuard
framework
Repository for TrustAgent code, safety regulations, assets/data, and experiment-running instructions.
agiresearch/TrustAgent
dataset
Repository containing SFT, RLAIF training, preference-data generation, evaluation code, dataset preparation guidance, and links to model checkpoints/datasets.
yonseivnl/vlm-rlaif
implementation
Official repository for TVLT with model code, pretraining and finetuning scripts, demos, setup documentation, and links to released checkpoints.
zinengtang/TVLT
A custom library referenced by the paper as the interface through which generated Python code controlled the Boston Dynamics Spot robot.
sheepskins/spottyai
system
GitHub repository for the Electricity Transformer Dataset used as ETTh1 and ETTm1 benchmark data in the experiments.
zhouhaoyi/ETDataset
dataset
Repository for a research demonstration of the Lean-Agent Protocol, including a frontend, FastAPI orchestrator, Lean worker, policy environment, audit log, and natural-language-to-Lean/back-translation workflow.
arkanemystic/lean-agent-protocol
framework
Python implementation of UAC, dataset preprocessing, ID and OOD training scripts, and temperature-scaling, entropy-maximization, and Laplace baselines.
Schindler-EPFL-Lab/UAC
Repository containing the authors' implementation of UMoE, the shared-expert architecture that unifies attention-MoE and FFN-MoE modules.
ysngki/UMoE
system
Author-provided code repository for the unbiased-alignment methods introduced in the paper.
cswjl/unbiased-alignment
Official Yandex Research repository containing implementations of experiments from this ICLR 2021 paper and the related proxy Dirichlet distillation work.
yandex-research/proxy-dirichlet-distillation
Meta Llama 3 model documentation for the open-weight model family; the paper evaluates LLaMA-3-8B and cites this GitHub model card.
meta-llama/llama3
TruthTorchLM is the library the paper states it uses to compare representative uncertainty and truthfulness methods in Section 6.
Ybakman/TruthTorchLM
Codebase extending tau^2-bench with runtime token-level UQ tracking, trajectory aggregation, uncertainty evaluation, and observation-UQ scoring.
deeplearning-wisc/agentuq
Repository associated with the uncertainty-manipulation attack and confidentiality-preserving audit protocol.
cleverhans-lab/confidential-guardian
system
Repository associated with training-dynamics-based selective classification experiments.
cleverhans-lab/sc
implementation
Repository associated with experiments and analysis for decomposing the selective-classification gap.
cleverhans-lab/sc-gap
implementation
Repository used to reproduce or support the private selective-classification experiments.
cleverhans-lab/selective-classification
implementation
The vLLM repository provides the production inference engine and fused MoE execution pipeline into which the authors integrate their activation-sparse routed-expert code path.
vllm-project/vllm
framework
Paper-associated GitHub path identified by the authors as the location of the study's code and data.
CyberScienceLab/Our-Papers
Official repository containing scripts for the paper's first- and second-order experiments across task labels, preferences, instructions, simulations, and free-form text.
minnesotanlp/artifacts-of-llmgendata
Repository accompanying the paper's controlled bias-generation, downstream evaluation, analysis, and mitigation experiments.
MiaomiaoLi2/bias-inheritance
Open-source package for replicating experiments, with raw trajectories hosted on Hugging Face, analysis scripts, and data referenced in the paper.
ARiSE-Lab/understanding-apr-agents
Official SWE-bench experiments repository used to retrieve public agent logs, trajectories, and patch diffs for studied configurations.
swe-bench/experiments
Repository containing metadata, analysis data, tools, and code for the cryptocoin correlation analysis.
quapsale/cryptoanalytics
dataset
Official Pythia repository for the model suite whose released checkpoints and reported downstream performance are analyzed as an external validation of the paper's loss-performance relationship.
EleutherAI/pythia
Official repository containing ITERATER datasets, preprocessing code, intent-classification code, revision-model training and evaluation code, and demonstration materials.
vipulraheja/IteraTeR
dataset
Repository for MAFBench, the unified benchmark suite introduced by the paper for controlled evaluation of multi-agent LLM frameworks.
CoDS-GCS/MAFBench
benchmark
Repository for ORCA, described as a step toward automating multi-agent system construction from high-level task descriptions using empirical benchmark evidence and cost-aware execution models.
CoDS-GCS/ORCA
system
Public Python repository containing data, source code, scripts, tests, results, analysis outputs, and paper figures for the Logic-in-LLMs study.
XAheli/Logic-in-LLMs
dataset
Repository released with the paper containing linguistic-rewrite data and resources for response generation, evaluation, and intervention experiments.
nobody294/linguistic_rule_triggers
dataset
Repository for the LLM-ification of CHI review, including sampled CHI papers, qualitative codes, metadata, taxonomy images, and supplementary materials.
rrrrrrockpang/llm-chi
dataset
Open-source implementation of LIME used by the authors to produce local feature-based explanations for the income prediction and biography classification tasks.
marcotcr/lime
package
Repository for the AndroidArena environment, benchmark task files, agent runners, replay/evaluation code, setup scripts, and related configurations.
AndroidArenaAgent/AndroidArena
benchmark
Microsoft's UniLM repository contains the implementation and released pre-trained models for the unified language model introduced in the paper.
microsoft/unilm
implementation
Official DeepMind repository containing the experimental curves and hyperparameters used to derive the paper's main scaling-law results, plus an example notebook for loading the data.
google-deepmind/scaling_laws_for_routing
Source code for USEagent, the unified software-engineering agent architecture evaluated in the paper.
nus-apr/USEagent
framework
Source code for USEbench, the unified software-engineering benchmark used to evaluate USEagent and baselines.
nus-apr/USEbench
dataset
Official implementation of CROSS for the paper, including model code, utilities for LLM temporal-chain embeddings, training scripts for temporal link prediction, logs, and dataset-preparation instructions.
SiweiPro/CROSS
framework
Official implementation containing SFT, DP fine-tuning, DPO, UnDial-based unlearning and regularization, true-prefix attacks, and task-evaluation scripts.
martonszep/llm-pii-leak
Repository released by the authors for the paper's universal and transferable LLM attack method and associated AdvBench artifacts.
llm-attacks/llm-attacks
Repository collecting materials related to data assessment and selection for language-model instruction tuning.
yuleiqin/fantastic-data-engineering
Provides data-preparation, SynDiff training and translation, tutorship, adaptation, nnU-Net inference, and evaluation workflows for out-of-distribution microscopy segmentation.
axondeepseg/AxonDeepSynth
Repository for the source code used in the paper's statistical-significance benchmark of online regression over multiple datasets.
mabushaera/Online-Regression-Statistical-Significance
benchmark
Repository for the TextFusionHTS framework and experiments reported by the paper.
xinzzzhou/TextFusionHTS
framework
Official project repository linked by the paper for the UProp method.
jinhaoduan/UProp
implementation
Official AgentBench codebase used for the Operating System agent evaluation.
THUDM/AgentBench
benchmark
Contains UrbanKGent inference code for RTE/KGC, baselines, prompts, sample SFT data, utilities, model-serving scripts, and LoRA fine-tuning code.
usail-hkust/UrbanKGent
Official Traversaal AI repository for UrduBench containing translated benchmark resources and evaluation notebooks.
traversaal-ai/urdubench_leaderboard
dataset
Official implementation of the precedent-based reaction-plausibility evaluator used as URSA's automated Solv-2 component.
insilicomedicine/ChemCensor
Official implementation of URSA, including route validation, building-block checks, collapsed route variants, ChemCensor scoring, and dataset-level Solv-N metrics.
insilicomedicine/URSA
Repository accompanying USF-MAE with pretraining code, preprocessing notebooks, pretrained checkpoints, figures, and access links for OpenUS-46.
Yusufii9/USF-MAE
dataset
Code repository for D3PO, the paper's reward-model-free direct preference fine-tuning method for diffusion models.
yk7333/D3PO
implementation
Repository containing code for Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning, including simulation pipeline, scripts, installation instructions, and training/evaluation commands.
UWRobotLearning/RISE
implementation
Repository containing code for cryptocurrency price prediction using RNN-based models and comparison of LSTM, GRU, and Bi-LSTM methods.
shamima08/Cryptocurrency-Price-Prediction-using-RNN
implementation
Repository for V-Rubrics with data conversion, SFT and GRPO training scripts, evaluation code, environments, tests, and release tooling.
shulin16/v-rubrics
Stable Baselines3 is cited as the implementation source for state-of-the-art baseline algorithms such as SAC, TD3, and PPO used in the experiments.
DLR-RM/stable-baselines3
package
Codebase for the variational-quantum-circuit DDPG/DQN portfolio agents, baselines, training, evaluation, and reproducibility workflow introduced in the paper.
VincentGurgul/qrl-dpo-public
framework
Microsoft's research repository contains a dedicated VATLM directory with training and model code and links to released checkpoints.
microsoft/SpeechT5
Flask repository used to illustrate semantic, Louvain, and label-propagation clustering over source files.
pallets/flask
Python Poetry repository used to demonstrate graph construction, object statistics, issue-driven retrieval, and top-k results.
python-poetry/poetry
Public repository implementing the VeinCast architecture, training curriculum, evaluation, and inference workflow introduced by the paper.
Zhisheng-researcher/VeinCast
implementation
OWASP IoTGoat is deliberately insecure OpenWrt-based firmware containing vulnerability challenges mapped to the OWASP IoT Top 10.
OWASP/IoTGoat
benchmark
A repository supplying complementary medical research skills discussed in the capability survey and used as part of the paper's skill ecosystem.
aipoch/medical-research-skills
The OpenClaw medical skills collection analyzed for its architecture, categories, composition, deployment model, and biomedical capability coverage.
FreedomIntelligence/OpenClaw-Medical-Skills
Official API and supporting resources for running the VirtualHome household simulator and executing activity programs.
xavierpuigf/virtualhome
dataset
Unity source code for constructing VirtualHome environments and translating activity programs into low-level executable character actions.
xavierpuigf/virtualhome_unity
Repository containing raw collected data, Study 1 to Study 3 folders, preregistration documents, analysis scripts written and executed by the system, analysis outputs, and manuscripts.
Explore-Science/Virtuous-Machines-Towards-Artificial-General-Science
dataset
Repository for the Matterport3D Simulator; it includes the R2R task assets/evaluation code and identifies this paper as the reference for the simulator and dataset.
peteanderson80/Matterport3DSimulator
benchmark
DMHouse, the modified DeepMind Lab and Quake-based indoor office simulator used to generate varied synthetic navigation environments for pre-training.
jkulhanek/dmlab-vn
Official implementation of the proposed navigation method, including simulation and TurtleBot training and evaluation code, model configurations, and links to released checkpoints and the real-world dataset.
jkulhanek/robot-visual-navigation
Official repository linked by the paper for Visual Semantic Entropy.
tadeephuy/visual-semantic-entropy
Official repository for the VLQA benchmark, project webpage, dataset access, and associated code resources.
shailaja183/vlqa
dataset
Repository identified by the paper as providing the ViTOED source code and dataset.
sonlam1102/vitoed
dataset
Official code repository for VLIS, including inference interfaces for BLIP-2, LLaVA, and Lynx and data and evaluation code for the landmark and character benchmarks.
JiwanChung/vlis
Repository for the VolleyBots environment, task suite, baseline implementations, and reproducible benchmark code.
thu-uav/VolleyBots
benchmark
Official implementation repository for the VoQA task, benchmark construction, evaluation, and question-alignment fine-tuning artifacts introduced by the paper.
AJN-AI/VoQA
benchmark
Official Voyager codebase, including the agent implementation and learned skill-library resources used to reproduce or apply the system described in the paper.
MineDojo/Voyager
Official repository for the VQA^2 instruction dataset, model family, training and evaluation implementation, and released project artifacts.
Q-Future/Visual-Question-Answering-for-Video-Quality-Assessment
Repository containing code associated with W-RAG weak-label generation and retriever fine-tuning experiments.
jmnian/WRAG
framework
Repository containing code and data for BadAgents, including poisoned data and code paths for Query-Attack, Observation-Attack, and Thought-Attack experiments.
lancopku/agent-backdoor-attacks
dataset
Continuously updated repository for tracking related works associated with the survey's human-view video-understanding taxonomy.
marinero4972/Awesome-HumanView-VideoUnderstanding
Official OpenAI repository implementing a re-creation of the weak-to-strong binary-classification setup, supported losses including the confidence auxiliary loss, and the supplementary AlexNet-to-DINO vision experiment.
openai/weak-to-strong
implementation
The GitHub repository hosts the WebArena code, browser environment, evaluation harness, configuration files, Docker environment resources, prompts, scripts, and reproduction materials for the paper.
web-arena-x/webarena
dataset
Repository for the WebShop environment, product and instruction setup, search engine, baseline rule/IL/RL models, tests, and sim-to-real transfer code.
princeton-nlp/WebShop
benchmark
Repository containing MEDQA data and baseline source code associated with the paper.
jind11/MedQA
dataset
Repository for the ICLR 2025 AI feedback tool that evaluated submitted reviews for vagueness or genericity, possible misunderstanding of the paper, and unprofessional tone, then generated private improvement suggestions.
zou-group/review_feedback_agent
system
Official code repository for SCRL, including the verl-based implementation, preprocessing instructions, and a training launch example.
Jasper-Yan/SCRL
implementation
LLMAgora, the configurable arena used to run two-agent scenarios with public utterances, private reflections, surveys, parameter sweeps, logging, and optional semantic, NLI, and emotion analyses.
danmohad/LLMAgora
Official repository containing code and data for the paper, including data preparation, reasoning-feature extraction, regression analysis, SAE analysis workflow, and test-time selection.
dayeonki/multilingual_reasoning
dataset
The robomimic repository contains the framework, algorithms, dataset interfaces, experiment configurations, and tooling associated with the paper's reproducible study.
ARISE-Initiative/robomimic
benchmark
Paper-linked GitHub URL for the BigData22 stock-movement dataset; the URL returned 404 during extraction, so repository availability was not verified.
stocktweet/stock-tweet
dataset
Repository associated with Hybrid Deep Sequential Modeling for Social Text-Driven Stock Prediction and its dataset.
wuhuizhe/CHRNN
dataset
Repository releasing a stock movement prediction dataset from tweets and historical stock prices.
yumoxu/stocknet-dataset
dataset
Repository for StockAgent, the LLM-based multi-agent stock trading simulation framework studied in the paper.
MingyuJ666/Stockagent
framework
A research-grade signal-only decision-support system for cross-sectional ranking of AI-focused U.S. equities with uncertainty quantification, regime-aware deployment gating, PIT-safe data handling, and walk-forward evaluation outputs.
sinsasanderink/AIStockForecaster-PIT-Safe-Ranking-First-Signals-for-AI-Equities-FMP-Kronos-FinText-TSFM-
framework
Repository containing code for reasoning-task experiments, computer-algebra calculations used in the appendices, and GPT-2/WikiText experiments associated with the paper.
eboix/relational-reasoning
implementation
Official implementation of OntoGraphRAG v1.0.0, the experiment harness, scripts for all tables and figures, per-query run logs, GPS replay stores, robustness artefacts, and reproducibility manifests used by the paper.
julka01/OntoGraphRAG
MM-TSFlib implementation used for Informer, FEDformer, PatchTST, iTransformer, and DLinear backbone experiments.
AdityaLab/MM-TSFlib
benchmark
TimeCMA codebase used as an evaluated aligning-based MMTS comparison.
ChenxiLiu-HNU/TimeCMA
implementation
LeRet codebase used as an evaluated aligning-based MMTS comparison.
hqh0728/LeRet
implementation
Time-LLM codebase used as an evaluated aligning-based comparison model.
KimMeen/Time-LLM
implementation
Codebase for the Context is Key forecasting benchmark, reproduced to examine LLM performance scaling.
ServiceNow/context-is-key-forecasting
benchmark
Repository containing an anonymized CAIA evaluator implementation, a benchmark.csv dataset with 178 evaluation questions, evaluation scripts for with-tool and without-tool settings, mock tools, prompts, and dependencies.
caiba-ai/caia-benchmark-0927
dataset
Car Crash Dataset (CCD), used by the paper to validate the vehicular accident-report use case based on mobile and edge LLM agents.
Cogito2012/CarCrashDataset
dataset
Repository containing classification and generation code for extracting linguistic and internal confidence, running ablations and analyses, preprocessing generation datasets, and reproducing reported confidence-correlation results.
HF-heaven/Correlation-between-Confidence-Measurements
Repository containing the compact RLHF pipeline, transition classifier, experiment configurations, analysis scripts, manuscript sources, result tables, figures, examples, and a Gradio-based response-comparison interface.
zabahana/rlhf-failure-modes-diagnostics
framework
Repository identified as the code for 'When Routing Collapses: On the Degenerate Convergence of LLM Routers'.
AIGNLAI/EquiRouter
implementation
Repository containing frozen audit artifacts and code used to reproduce the reported NAVSIM score-basis conditions and numerical diagnostics.
WZiang/navsim-score-basis-audit
Repository stated by the paper as the location where code and data for AgentDebug will be available.
ulab-uiuc/AgentDebug
dataset
NVIDIA's transformer inference engine, extended in the paper with DeepSpeed MoE support, TUPE attention, expert routing, quantized MoE computation, and batch pruning.
NVIDIA/FasterTransformer
framework
OpenManus repository cited by the paper for one of the multi-agent frameworks evaluated in MAST-Data.
mannaandpoem/OpenManus
Official repository containing code and data for the paper, including taxonomy definitions/examples, traces, inter-annotator annotations, and the LLM judge pipeline.
multi-agent-systems-failure-taxonomy/MAST
Repository containing prompts, research ideas, selected outputs, and failure analyses for the four autonomous research attempts, including MARL-idea, SALVO-WM-idea, SDTS-WM-idea, SemEnt-ALGN-idea, and workflow prompts.
Lossfunk/ai-scientist-artefacts-v1
Author-linked repository for the WikiHow summarization dataset introduced by the paper.
mahnazkoupaee/WikiHow-Dataset
dataset
Repository for preparing, analyzing, and visualizing survey responses for the 'Will Agents Replace Us?' preprint project, including Python scripts for data preparation, exploratory analysis, inferential analysis, and manuscript figure generation.
nkkko/agent-perceptions
dataset
Repository for DeepFund, a platform intended to evaluate LLM trading capability across financial markets using a unified environment, multi-agent system, external information ingestion, trading decisions, and arena-style performance presentation.
HKUSTDial/DeepFund
framework
Repository for Latency Sensitive Benchmarks, including HFTBench and StreetFighter benchmark code and evaluation examples for latency-aware LLM-agent assessment.
HaoKang-Timmy/LatencySensitiveBench
benchmark
Repository linked by the paper for the proposed automated wireless-agent workflow design system.
jwentong/WirelessAgent-R2
framework
Repository for WirelessBench, including the wireless tasks and released scoring code.
jwentong/WirelessBench
dataset
ParlAI repository containing the Wizard of Wikipedia task integration and project code used to distribute and evaluate the benchmark and associated models.
facebookresearch/ParlAI
Official project repository containing the WizardCoder code/resources and linking the ICLR 2024 WizardCoder paper.
nlpxucan/WizardLM
Framework used for running, managing, and reproducing web-agent experiments on BrowserGym benchmarks.
ServiceNow/AgentLab
implementation
Open-source Gym-style browser environment for implementing and evaluating web agents with rich observations and action spaces.
ServiceNow/BrowserGym
framework
Open-source benchmark package for evaluating browser agents on ServiceNow-based knowledge-work tasks.
ServiceNow/WorkArena
dataset
OpenBMB/WorkflowLLM is the official repository for the WorkflowLLM project, described as a data-centric framework for enhancing LLM workflow orchestration with WorkflowBench and WorkflowLlama resources.
OpenBMB/WorkflowLLM
dataset
Official repository for World Action Planner, including environments, world-model code/client, setup instructions, checkpoints, and a demo notebook for imagined actions.
XiangchengZhang/world-action-planner
implementation
Repository for the W2C pipeline, generated-data workflow, and associated LLaVA training and evaluation materials.
foundation-multimodal-models/World2Code
Official implementation artifact for Worldscape-MoE, including training and inference entry points, modality-specific data preparation, validation tools, and optional offline VAE encoding.
EmbodiedCity/Worldscape-MoE.code
Official code repository for training and evaluating Direct Preference Head models, including benchmark evaluation scripts and links to released model checkpoints.
Avelina9X/direct-preference-heads
implementation
NEORV32 is the architecturally distinct target SoC used to test whether training supervision generated from PicoSoC specifications transfers without target-design supervision.
stnolting/neorv32
PicoSoC, a simple SoC built around PicoRV32, is the source architecture for the zero-shot IP-level transfer study.
YosysHQ/picorv32
Repository for the paper's XGBoost-based NEPSE log-return forecasting workflow and benchmark outputs.
sahajrajmalla/nepse-xgboost-forecasting
dataset
Public repository containing the cost-aware LLM routing system, training/data-preprocessing components, evaluation and serving pipeline, router tests, and documentation.
SalesforceAIResearch/xRouter
framework
Code, scripts, notebooks, data assets, and FixMatch integration for reproducing DIPS tabular and computer-vision experiments.
seedatnabeel/DIPS
implementation
Official implementation of ZipCache, including package setup and an inference demonstration.
ThisisBillhe/ZipCache
Official implementation of ZSMerge with model-specific attention modules, tests, datasets, and scripts for throughput and ROUGE experiments.
SusCom-Lab/ZSMerge