Category
9,568 papers
Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches provide execution flexibility but do not explicitly model subtask hierarchies or dependencies, while predefined workflows impose this structure but fix the decomposition be...
Language model agents increasingly automate post-training, but when given the full training stack they converge on supervised fine-tuning and spend most effort revising training data. Existing systems give the agent one kind of control, selecting rows from a fixed pool or calling a generator, whereas a human data engin...
LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption against a minimal adversary. In a ten-agent factual discussion, one or three adversarial agents repeatedly assert a plausible false answer. After eac...
RoleQ is introduced, a quantization framework that places scales by the functional roles of Transformer units rather than by the layout of the weight matrix, as conventional formats do, and leads every post-training ternary method at matched or lower memory-resident bits on perplexity, zero-shot accuracy and MMLU.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shapes agent behavior and policy learning in computer-aided design (CAD), a professional domain characterized by persistent state, geometric constraints, a...
A standard decidable regime used in practice is identified under which exhaustive simulation yields a terminating search procedure with the desired guarantees, and the limit of this recovery is shown: a chain of accepted updates can raise the bounded score in every round while the true score falls.
Understanding how the human brain constructs meaning from real-world language remains a fundamental challenge, as semantics depend on context that varies in natural settings. To enable the study of real-world linguistic meaning in the brain, we introduce SCRIBE, a framework grounded in a neuroscience-informed semantic...
Large language models (LLMs) predict neural responses during naturalistic language comprehension, but the linguistic information underlying this brain alignment remains difficult to interpret. We use SCRIBE, an interpretable contextual semantic representation spanning 65 neurocognitively grounded semantic properties, a...
Scientific agents must connect research problems, methods, and findings dispersed through narrative articles. We introduce SPRA (Structured Paper Representation for Agents), a paper-level representation of persistent research objects and typed relations. Its empirical-AI profile organizes Problems, Contributions, Compo...
DocPilot is introduced, an agentic document framework that supports expressive orchestration and makes complex document solving learnable by small language models (SLMs) and integrates local visual inspection, code-based numerical reasoning, and cross-modal reasoning for multimodal understanding.
Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving such disagreements is difficult because agents'decisions are susceptible to non-semantic biases such as majority pressure and response-style...
Trustworthy biomedical AI requires reliable action selection when evidence is missing, stale, conflicting, or late, not only accurate answers on static inputs. We instantiate an episode-level evaluation protocol as 400 synthetic healthcare workflow episodes: 40 hand-authored semantic seeds across four task classes, two...
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
