AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsThe Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows
arXiv:2610.31985v1 Announce Type: new Abstract: LLM agents are increasingly deployed in collaborative settings where they pursue separate tasks while sharing resources and operating under review or oversight processes. S…
- arXiv cs.AIagentsCEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition
arXiv:2610.32022v1 Announce Type: new Abstract: Intent recognition in human-robot interaction requires agents to resolve ambiguous natural language instructions by inferring the speaker's underlying goals. Research has i…
- arXiv cs.AIagentsBARC-Bench: Benign Asks, Risky Consequences
arXiv:2610.32024v1 Announce Type: new Abstract: Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce…
- arXiv cs.AIagentsRSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training
arXiv:2610.32026v1 Announce Type: new Abstract: Conventional neural-network training typically follows a predefined optimization recipe, motivating a LLM agent that monitors training dynamics and adjusts optimizer settin…
- arXiv cs.AIagentsDo AI-for-Science Agents Preserve Model Safety?
arXiv:2610.32045v1 Announce Type: new Abstract: AI-for-Science agents are increasingly being used for formulating scientific hypotheses, running autonomous experiments, and interpreting evidence. These agents are constru…
- arXiv cs.AIagentsUnderstanding Communication Failures in Multi-Agent LLM Systems
arXiv:2610.32060v1 Announce Type: new Abstract: Multi-agent LLM systems aim to improve reasoning through debate, evidence sharing, and mutual correction, but interaction can also introduce failures that final accuracy al…
- arXiv cs.AIagentsDriveMind: Mind-Evolving Belief Tracking for Closed-Loop Autonomous Driving
arXiv:2610.32069v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) can perceive a traffic scene, reason about it, and propose a driving action within a single model. However, existing MLLM-ba…
- arXiv cs.AIagentsBehaviour analysis for large language model-driven agents
arXiv:2610.32087v1 Announce Type: new Abstract: Understanding language-agent behaviour requires learning how actions are organised across a trajectory and how this organisation relates to context and outcomes. We propose…
- arXiv cs.AIagentsPersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers
arXiv:2610.32106v1 Announce Type: new Abstract: Scientific agents collaborate with researchers whose expertise and preferences differ, but benchmarks usually hold the collaborator fixed. We introduce PersonaScienceBench:…
- arXiv cs.AIagentsWho Verifies the Tools? How Warped Formatters Mislead Agents and Their Verifiers
arXiv:2610.32110v1 Announce Type: new Abstract: Agents and verifiers often rely on the text a tool prints, and that text can misrepresent what the tool actually did, even when the tool's computation is correct. We saw th…
- arXiv cs.AIagentsSWE-Shift: Evaluating Coding Agents in Evolving Workspaces
arXiv:2610.32196v1 Announce Type: new Abstract: Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime st…
- arXiv cs.AIagentsCorrect Answers, Closed Gates: SolveBind for GUI Agents at the Verification Barrier
arXiv:2610.32223v1 Announce Type: new Abstract: Websites and applications deploy CAPTCHAs and anti-automation mechanisms that use behavioral signals such as interaction trajectories and timing, not outcomes alone, to dis…
- arXiv cs.AIagentsFinancial Context-Rich Strategy for Actor-Critic based Agents: A Deep Reinforcement Learning Approach for Stock Trading
arXiv:2610.32237v1 Announce Type: new Abstract: In modern financial markets, more than 3/4th of the large volume trade is executed by algorithmic trading based on advanced trading strategies to attain higher precision an…
- arXiv cs.AIagentsMinimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical
arXiv:2610.32245v1 Announce Type: new Abstract: AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve be…
- arXiv cs.AIagentsRSIHub: A Composable Framework for Agent-Evolution Methods
arXiv:2610.32253v1 Announce Type: new Abstract: Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery…
- arXiv cs.AIagentsMedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports
arXiv:2610.32258v1 Announce Type: new Abstract: Although Large Language Models (LLMs) have demonstrated potential in clinical documentation, generating the rigorous, evidence-based reasoning required for unprecedented, a…
- arXiv cs.AIagentsTrial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
arXiv:2610.32285v1 Announce Type: new Abstract: LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation.…
- arXiv cs.AIagentsLifelong Context Adaptation through Bidirectional Memory-Skill Learning
arXiv:2610.32295v1 Announce Type: new Abstract: Lifelong LLM agents must learn from an expanding history of interactions while making each decision within a bounded context window. Memory makes past experience available,…
- arXiv cs.AIagentsDMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
arXiv:2610.32305v1 Announce Type: new Abstract: Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop. Self-reflection, in which an agent critiques i…
- arXiv cs.AIagentsBeyond Gain: Measuring Skill Internalization for Agent Skill Retirement
arXiv:2610.32322v1 Announce Type: new Abstract: LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models. As models improve, a hub must find the skills a given model has int…
- arXiv cs.AIagentsTGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent
arXiv:2610.32326v1 Announce Type: new Abstract: Large Language Model (LLM) agents have enabled automated code evolution for algorithm discovery. However, current recursive self-improvement (RSI) research for sequential r…
- arXiv cs.AIagentsAdaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents
arXiv:2610.32370v1 Announce Type: new Abstract: Controlling scientific instruments requires parameters to be adjusted progressively in response to feedback from successive operations. When unobserved operating conditions…
- arXiv cs.AIagentsDealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage
arXiv:2610.32380v1 Announce Type: new Abstract: Large language models (LLMs) can read startup pitch decks, but letting them emit investment scores directly invites score inflation, run-to-run variance and rationales that…
- arXiv cs.AIagentsLeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents
arXiv:2610.32412v1 Announce Type: new Abstract: Recursive large language model (LLM) agents solve long-horizon tasks through decomposition, execution, and environmental feedback. Yet after producing an atomic subtask, th…
- arXiv cs.AIagentsAsync-RBench: Benchmarking Asynchronous Task Execution in LLM Agents
arXiv:2610.32429v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute tasks asynchronously: a main agent continues working while its subagents run, and the task state may change before th…
- arXiv cs.AIagentsPOSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories
arXiv:2610.32448v1 Announce Type: new Abstract: Training environments remain a major bottleneck for agents in data-driven scientific discovery. Existing collections of executable and verifiable training environments are…
- arXiv cs.AIagentsCauProphet: Teaching Agents to Develop Causal Cognition like Humans
arXiv:2610.32477v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly support long-horizon tasks by leveraging external memory and past experience. However, existing agents mainly retrieve re…
- arXiv cs.AIagentsWhen Agents Fail: Model or Harness--Who's to Blame?
arXiv:2610.32483v1 Announce Type: new Abstract: LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated th…
- arXiv cs.AIagentsIGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints
arXiv:2610.32536v1 Announce Type: new Abstract: GUI grounding benchmarks ask whether an agent can localize a target that is already visible in a static screenshot. Real interfaces often violate this assumption: a target…
- arXiv cs.AIagentsWhat Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
arXiv:2610.32620v1 Announce Type: new Abstract: LLM agents optimize a ligand in a protein pocket by editing it step by step and docking each edit. Recent agents first spend extra dockings probing the complex with control…
- arXiv cs.AIagentsAgentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication
arXiv:2610.32738v1 Announce Type: new Abstract: Hazard maps are essential tools for public risk communication, preparedness, and evacuation planning, yet effective cartographic design is not always ensured due to limited…
- arXiv cs.AIagentsActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents
arXiv:2610.32752v1 Announce Type: new Abstract: LLM agents need long-term memory that can recover precise and mutually consistent evidence from growing interaction histories, particularly when answers depend on relations…
- arXiv cs.AIagentsHarnessMM: Recursive Self-Improvement for Harness Token Efficiency
arXiv:2610.32813v1 Announce Type: new Abstract: Agent harnesses repeatedly invoke reasoning after tool feedback, even when an earlier call has already fixed the next action. We introduce HarnessMM (Harness Minus Minus),…
- arXiv cs.AIagentsReimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves
arXiv:2610.32851v1 Announce Type: new Abstract: Enterprises are deploying agentic AI across the software development lifecycle, and they need the behavioral logic of the systems they act on, not stakeholder documentation…
- arXiv cs.AIagentsDo "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations
arXiv:2610.32874v1 Announce Type: new Abstract: In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previous probability and the probabilities reported by its ne…
- arXiv cs.AIagentsSemantEq: Faithful Bidirectional Equivalence of Formal Statements
arXiv:2610.32919v1 Announce Type: new Abstract: Statement autoformalization translates mathematics from natural language into a proof assistant such as Lean 4, and models now do it at scale. As provers get stronger, the…
- arXiv cs.AIagentsAn Agentic Approach with Evidence-Grounded Verification for Multimodal Emotion Reasoning in Conversation
arXiv:2610.31685v1 Announce Type: cross Abstract: LLM-based multimodal emotion reasoning systems perform well on standard benchmarks, but improving them through instruction tuning can be computationally expensive. Agenti…
- arXiv cs.AIagentsBefore the Ticket: Grounding HPC User Support in Documentation and Resolved Tickets with an Agentic LLM Assistant
arXiv:2610.31703v1 Announce Type: cross Abstract: Most questions that reach an HPC help desk have already been answered in the center's user guides or in a ticket someone else filed last semester; users still file new ti…
- arXiv cs.AIagentsRubricCraft: Where Solutions Diverge, Criteria Emerge
arXiv:2610.31707v1 Announce Type: cross Abstract: Evaluating language agents on open-ended, artifact-producing tasks is difficult: model-based graders can be inconsistent, while exhaustive programmatic checks are often i…
- arXiv cs.AIagentsMining the Design Space of Multi-Agent Workflows
arXiv:2610.31709v1 Announce Type: cross Abstract: Designing large language model (LLM) multi-agent systems (MAS) still relies on trial and error and informal "folk wisdom." Manual studies test only a few communication st…
- arXiv cs.AIagentsCompact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents
arXiv:2610.31710v2 Announce Type: replace-cross Abstract: Context compaction lets long-horizon coding agents continue beyond their context windows, but can erase the state needed to finish a task. Prior evaluations measu…
- arXiv cs.AIagentsMBABench-2.0: Evaluating AI Agents on Constructing Financial Spreadsheets Beyond Simple Verifiability
arXiv:2610.31711v1 Announce Type: cross Abstract: Spreadsheets are the lingua franca of modern finance, driving valuation, forecast, audit, and many other core workflows of the industry. As LLM agents advance to automate…
- arXiv cs.AIagentsReuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control
arXiv:2610.31712v1 Announce Type: cross Abstract: Mobile GUI agents frequently perform repetitive tasks with similar interaction procedures. Reusing previous executions can reduce redundant LLM inference and execution ov…
- arXiv cs.AIagentsWhat Open-Source Projects Tell Their Coding Agents: A Census of AGENTS.md and CLAUDE.md
arXiv:2610.31715v2 Announce Type: replace-cross Abstract: Coding agents can be guided with instruction files in a repository. We examine this emerging practice through a census of 22,854 popular, active GitHub repositori…
- arXiv cs.AIagentsBenchmarks Are Surprisingly Compaction-Friendly
arXiv:2610.31778v1 Announce Type: cross Abstract: Long horizon agentic tasks are now pushing LLM agents past their context window. To continue the task, the agent scaffold has to free up the context window, a process kno…
- arXiv cs.AIagentsSWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?
arXiv:2610.31854v1 Announce Type: cross Abstract: Greenfield software development in freelance settings requires coding agents to turn incomplete client requests into working software. This makes requirement clarificatio…
- arXiv cs.AIagentsKnowing When to Stop: The Evidence-Action Gap in Coding Agents
arXiv:2610.31895v2 Announce Type: replace-cross Abstract: Coding agents are trained to complete tasks, and they keep trying even when the environment makes completion impossible. The evidence that only outside help can r…
- arXiv cs.AIagentsAgentic AI Defense: Decode-Time Provenance Binding for MCP
arXiv:2610.31974v1 Announce Type: cross Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust lau…
- arXiv cs.AIagentsAgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
arXiv:2610.32092v1 Announce Type: cross Abstract: Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active wat…
- arXiv cs.AIagentsImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation
arXiv:2610.32120v1 Announce Type: cross Abstract: Complex text-to-image requests remain difficult to satisfy reliably. Verifying and repairing an image can fix an individual output, but a successful repair does not neces…