Llm-Agents

TL;DR for operators Wang et al. study a deployment problem that is easy to underestimate: an RL-trained agent can work well before compression or modification and then fail badly after its policy is perturbed.1 Their proposed method, Stable Perturbation-Robust Policy Optimization (SPrPO), trains the agent under perturbations while allocating less noise to locally sensitive FFN channels and adjusting total perturbation strength using a gradient-based improvement proxy. ...

TL;DR for operators In World Agent: Can Language Models Keep a World Running?1, the central problem is not whether an agent can produce the expected event. It is whether those events remain correctly organized as the world evolves. Across the benchmark, models often complete more required events than they correctly satisfy the relationships among those events. Causal-relation checking is especially fragile: its cross-model mean falls from 0.683 in the Easy maintenance tier to 0.356 in Extreme, where substantially more of the world representation must be constructed by the agent. ...

TL;DR for operators An agent can have a compressed memory that answers the current question perfectly and is already inadequate for the next update. Guangzhe Zhang’s Correct Now, Insufficient Later: Auditing Update Sufficiency in Context Compression1 demonstrates the problem with paired synthetic histories. On DeepSeek, the paper’s frontier selector and a latest-only variant both score 96/96 on current reads. After a later update makes older evidence relevant, frontier remains at 96/96, while latest-only falls to 32/96. ...

TL;DR for operators An autonomous security agent can notice far more suspicious code paths than it can fully prove vulnerable during a fixed audit window. In the paper’s 300-trajectory analysis, verification consumed 73.8% of wall-clock time, compared with 7.3% for hypothesis formation; verifying one hypothesis took about 11.1 times as much time as generating one. ...

TL;DR for operators A shared enterprise assistant does not only need to remember more people. It must often determine which fact, permission, instruction, or decision has to exist before another action is valid. Org-Agent addresses this by decomposing multi-user work into atomic subtasks, connecting prerequisite relationships in a dynamic execution graph, ordering those subtasks so prerequisites run first, and carrying retrieved evidence and intermediate results into later steps.1 ...

TL;DR for operators An agent that repeatedly uses a procedure and receives high task reward still has not shown that the procedure deserves permanent promotion into its reusable playbook. R² Flow separates three questions that agent systems often blur together: how much a skill participates in successful execution, whether choosing that skill actually improves outcomes relative to alternatives, and whether there is enough independent evidence to authorize a persistent library change. Across eight recursive phases, the paper reports mean held-out OOD score rising from 71.2 to 81.02, with 33 of 37 committed edits improving held-out verified score. By contrast, reward-derived edit labels can raise training reward while lowering that verified score. ...

TL;DR for operators Enterprise agents repeatedly entering the same document stores, applications, and tool environments often spend task-time compute rediscovering where information lives and how the environment behaves. The alternative tested here is to perform some of that discovery before real requests arrive and preserve what was learned as reusable artifacts. Samuel et al.’s Studying Without a Syllabus: Task-Agnostic Environment Preprocessing1 reports that 21 of 24 studied method-by-benchmark conditions improve over running the frozen solver with no preparation. The stronger result is not that more preparation is always better. A preparation strategy that works well in one environment can perform poorly in another, and larger study budgets do not reliably increase downstream reward. ...

TL;DR for operators Bio-MemArt1 addresses a problem that ordinary memory retrieval does not solve: a memory can be highly relevant to a query and still belong to the wrong user. Its intervention is deliberately narrow. Each persistent KV-memory block receives a biometric owner template. At query time, the current face or palmprint representation is compared with those templates. Memories that fail a calibrated similarity threshold are excluded before semantic retrieval begins. The original MemArt retrieval and generation machinery then operates only on the surviving memories. ...

TL;DR for operators When an LLM produces a bad executable workflow, the failure may not mean that it misunderstood the business rule. It may have selected the right actions and still lost parameters, Boolean relationships, or graph ordering while writing the full structure. That distinction changes the engineering response. In Generating Workflow DAGs from Natural Language with Non-Reasoning LLMs, Anand Iyer, Bhanu Khetharpal, Srinivas Upadhya, and Ramkumar Rajagopal test an architecture that keeps language interpretation in the LLM but moves deterministic graph expansion into conventional code.1 On their 635-rule benchmark, GPT-5.3-chat improves from 56.4% to 80.6% LLM-judge validity when paired with registry selection, a compact intermediate representation, and deterministic compilation. Exact-condition accuracy rises from 56.5% to 82.2%. ...

TL;DR for operators Suppose several business units or partner organizations run different agent workflows. Each has its own prompts, tools, communication patterns, and failure cases. They want a common safety layer, but centralizing those interaction traces would expose precisely the operational data they are trying to protect. The harder problem is that a guard trained elsewhere may not transfer well enough to solve this. In the reported experiments, an architecture-matched topology guard scores 0.512 AUROC when transferred off the shelf to Agent-SafetyBench, but 0.695 after in-domain retraining. Local adaptation helps, yet isolated local training is also weaker than collaborative training and becomes fragile when client labels are highly skewed. ...