LLM

TL;DR Classical planners crack under scale. You can rescue them with LLMs in two ways: (1) Inspire the next action, or (2) Predict an intermediate state and split the search. On diverse benchmarks (Blocks, Logistics, Depot, Mystery), the Predict route generally solves more cases with fewer LLM calls, except when domain semantics are opaque. For enterprise automation, this points to a practical recipe: decompose → predict key waypoints → verify with a trusted solver—and only fall back to “inspire” when your domain model is thin. ...

Executive takeaway: Efficient LLM architectures aren’t just academic: they reset the economics of AI products by cutting context costs, shrinking GPUs per QPS, and opening new form factors—from phone-side agents to ultra-cheap serverless endpoints. The winning strategy is hybrid by default, KV-light, and latency-budgeted. Why this matters now If you ship with AI, your margins live and die by three levers: sequence length, active parameters per token, and memory traffic. Classical Transformers lose on all three. The latest wave of “speed-first” designs offers a menu of swaps that trade negligible accuracy for step-change gains in throughput, tail latency, and $ per million tokens. This survey gives us a clean taxonomy and—more importantly—the design intent behind each family: compress the compute (linear & sparse sequence modeling), route the compute (MoE), restructure the compute (efficient full attention), and rethink the decoder (diffusion LLMs). ...

Large language models can forecast surprisingly well when you hand them the right context. But naïve prompts leave money on the table. Today’s paper introduces four plug‑and‑play strategies—ReDP, CorDP, IC‑DP, RouteDP—that lift accuracy, interpretability, and cost‑efficiency without training new models. Here’s what that means for teams running demand, risk, or ops forecasts. Why this matters for business readers Most production forecasts are numeric workhorses (ARIMA/ETS/TS foundation models), while contextual facts—weather advisories, policy changes, promos, strikes—arrive as text. LLMs can read that text and adjust the forecast, but simply stuffing history+context into a prompt (“direct prompting”) is often fragile. The four strategies below are operational patterns you can drop into existing stacks without re‑architecting. ...

When it comes to reasoning, bigger isn’t always better. Large language models (LLMs) often produce unnecessarily long chains of thought, burning through tokens — and budgets — even for simple problems. While fixed token limits during training can force brevity, they also rob models of the chance to first explore and then compress their reasoning. A new study, Train Long, Think Short, proposes a smarter path: curriculum learning for length control. Instead of a one-size-fits-all cap, the model starts with a generous token budget, learns robust reasoning strategies, and then gradually adapts to shorter limits over time. The result is a model that solves complex tasks with fewer tokens, without losing accuracy. ...

From Static Scripts to Living Workflows The AI agent world has a scaling problem: most automated workflow builders generate one static orchestration per domain. Great in benchmarks, brittle in the wild. AdaptFlow — a meta-learning framework from Microsoft and Peking University — proposes a fix: treat workflow design like model training, but swap numerical gradients for natural language feedback. This small shift has a big implication: instead of re-engineering from scratch for each use case, you start from a meta-learned workflow skeleton and adapt it on the fly for each subtask. ...

Most AI conversations equate “emotional intelligence” with sentiment labels. Humans don’t work that way. We appraise situations—Was it fair? Could I control it? How much effort will this take?—and then feel. This study puts that lens on large language models and asks a sharper question: Do LLMs reason about emotions through cognitive appraisals, and are those appraisals human‑plausible? What CoRE Actually Measures (and Why It’s Different) CoRE — Cognitive Reasoning for Emotions evaluates seven LLMs across: ...

When you think of AI in public decision-making, you might picture chatbots handling service requests or predictive models flagging infrastructure risks. But what if we let large language models (LLMs) actually allocate resources—acting as digital social planners? That’s exactly what this new study tested, using Participatory Budgeting (PB) both as a practical decision-making task and a dynamic benchmark for LLM reasoning. Why Participatory Budgeting Is the Perfect Testbed PB is more than a budgeting exercise. Citizens propose and vote on projects—parks, public toilets, community centers—and decision-makers choose a subset to fund within a fixed budget. It’s a constrained optimization problem with a human twist: budgets, diverse preferences, and sometimes mutually exclusive projects. ...

The AI Pressroom Arrives — Mostly Unannounced When ChatGPT-3.5 launched in late 2022, it didn’t just disrupt classrooms and coding forums — it quietly walked into newsrooms. A recent large-scale study of 40,000+ news articles shows that local and college media outlets, often operating with lean budgets and smaller editorial teams, have embraced generative AI far more than their major-network counterparts. And in many cases, readers have no idea. The research, spanning opinion sections from CNN to The Harvard Crimson, and across formats from print to radio, found a tenfold jump in AI-written local news opinion pieces post-GPT. College newspapers followed closely with an 8.6× increase, while major outlets showed only modest uptake — a testament to stricter editorial controls or more cautious adoption policies. ...

When business leaders ask for a “quick chart,” they rarely expect to become detectives in the aftermath—trying to work out why the AI picked that chart type, grouped the data that way, or left out important categories. Yet that’s exactly the frustration with most Natural Language to Visualization (NL2VIS) tools today: they generate results like a magician pulling a rabbit from a hat, with no insight into how the trick was done. ...

When you chat with a VTuber’s AI twin or a game NPC that remembers your past adventures, breaking character can ruin the magic. Large language models (LLMs) have the raw conversational talent, but keeping them in character—especially when faced with questions outside their scripted knowledge—is notoriously difficult. AMADEUS, a new RAG-based framework, aims to fix that. The Problem with Persona Drift Most role-playing agents (RPAs) rely on a static “persona paragraph” to define who they are. Retrieval-Augmented Generation (RAG) can pull relevant persona chunks into context, but three problems persist: ...