AI news archive.
4,958 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsSkillCT: A Multidimensional Benchmark and Execution-Free Baseline for Agent Skill Assessment
arXiv:2610.38147v1 Announce Type: new Abstract: Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories. However, existing skill be…
- arXiv cs.AIagentsDecompGym: Benchmarking LLM Agents on Designing Decomposition Algorithms
arXiv:2610.38175v1 Announce Type: new Abstract: Benders decomposition and column generation solve large optimization problems by passing cuts, columns, and dual values between a master problem and subproblems, and are ha…
- arXiv cs.AIagentsFrom Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis
arXiv:2610.38201v1 Announce Type: new Abstract: Designing power electronics converters traditionally requires intensive human expertise across topology sizing, commercial component selection, circuit simulation verificat…
- arXiv cs.AIagentsDisparity Laundering: Consensus Without Fairness in Clinical Multi-Agent Systems
arXiv:2610.38215v1 Announce Type: new Abstract: Clinical large language models are increasingly fielded as multi-agent teams, on the assumption that deliberation averages out individual error. It does not average out bia…
- arXiv cs.AIagentsFACTS-MAS: A Multi-Agent Architecture for Adaptive Forecasting from Heterogeneous Evidence
arXiv:2610.38225v1 Announce Type: new Abstract: Real-world forecasting often requires integrating heterogeneous evidence whose predictive value varies across horizons, operating regimes, and domains. We introduce FACTS-M…
- arXiv cs.AIagentsInvestor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
arXiv:2610.38342v1 Announce Type: new Abstract: Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks asses…
- arXiv cs.AIagentsSCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
arXiv:2610.38391v1 Announce Type: new Abstract: Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories c…
- arXiv cs.AIagentsMasked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
arXiv:2610.38392v1 Announce Type: new Abstract: Self-improving LLM agents edit their own harness, the prompts and rules around a fixed model, and keep an edit only if an acceptance gate scores it higher on a batch of tas…
- arXiv cs.AIagentsAgent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
arXiv:2610.38398v1 Announce Type: new Abstract: The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network conn…
- arXiv cs.AIagentsGovernance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
arXiv:2610.38411v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional FL provides limited runtime governance, evidence verification, fa…
- arXiv cs.AIagentsPredict the Reward, Not the World: World Reward Models for ML Agents
arXiv:2610.38439v1 Announce Type: new Abstract: Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing them, and keeping the best. Execution gives the search reliable feedba…
- arXiv cs.AIagentsAn Alignment Benchmark for Enterprise Agents on Era by Eon
arXiv:2610.38544v1 Announce Type: new Abstract: AI agents are widely used in enterprises to access business systems and act on them in pursuit of a goal. However, fulfilling a user's request can cause harm. Era by Eon is…
- arXiv cs.AIagentsCALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
arXiv:2610.38573v1 Announce Type: new Abstract: A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past. Relevance-based retrieval overlooks this tension: semantic relevance, evid…
- arXiv cs.AIagentsThink Before You Act: Decision Gate for LLM Agents
arXiv:2610.38620v1 Announce Type: new Abstract: LLM agents increasingly perform consequential actions through external tools, yet their proposed actions are often executed without independent verification of policy compl…
- arXiv cs.AIagentsRight Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries
arXiv:2610.38631v1 Announce Type: new Abstract: Financial assistants answer questions that sound factual but depend on what the user leaves unsaid: what a data figure measures, which product variant is meant, and the inv…
- arXiv cs.AIagentsCurriculum-Based Deep Reinforcement Learning for Robust Autonomous Rocket Landing under Atmospheric Uncertainty
arXiv:2610.38636v1 Announce Type: new Abstract: Autonomous far-range rocket landing is a challenging control problem because navigation, descent-rate regulation, attitude management, and fuel use must be coordinated in t…
- arXiv cs.AIagentsBeyond fabrication: Misattributed numbers in papers written by AI research agents
arXiv:2610.38691v1 Announce Type: new Abstract: Verifying numerical claims in research written by AI agents is an important but challenging problem. Recent benchmarks show that many agent-written papers fail integrity ch…
- arXiv cs.AIagentsWhere You Inject Matters: The Trust Region Effect in LLM Agents
arXiv:2610.38867v1 Announce Type: new Abstract: LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments. Despite their growing capabilities, these agents remain vulnerabl…
- arXiv cs.AIagentsAuditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
arXiv:2610.38869v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being used as cognitive interfaces that shape how users interpret evidence, communicate, and make decisions. As deployed syste…
- arXiv cs.AIagentsAligning Autoresearch: Co-Improvement between Agents and Humans
arXiv:2610.38882v1 Announce Type: new Abstract: Autoresearch agents can now attempt long-horizon AI research end-to-end, i.e., self-improvement. However, best results are still obtained by research agents interacting wit…
- arXiv cs.AIagentsTreasuryQA Bench: Can AI Agents Work an Archive of Scanned Financial Records?
arXiv:2610.38924v1 Announce Type: new Abstract: Organisations keep decades of financial records as scanned PDFs on shared drives, and AI agents can now reach those drives through Model Context Protocol (MCP) servers. Exi…
- arXiv cs.AIagentsEfficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality Consolidation
arXiv:2610.38960v1 Announce Type: new Abstract: Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed eviden…
- arXiv cs.AIagentsAgentic AI Reasoning and Learned Sampling for Task-Aware Projection Selection in Sparse-View CT: Predicting Hemodynamics
arXiv:2610.39003v1 Announce Type: new Abstract: Sparse-view computed tomography (CT) reduces the number of acquired projections, but conventional sampling strategies are designed primarily for image reconstruction rather…
- arXiv cs.AIagentsGoal-Aware Dynamic Multi-Agent Collaboration for Long-Horizon Tasks
arXiv:2610.39193v1 Announce Type: new Abstract: LLM-based agents are increasingly used to complete complex, long-horizon tasks without human intervention. To make progress toward the task goal, agents need to perform dif…
- arXiv cs.AIagentsWhere to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents
arXiv:2610.39251v1 Announce Type: new Abstract: Trajectory-level GRPO is a common approach for training multi-step GUI agents, but repeatedly rolling out complete trajectories from the task root can be inefficient: task-…
- arXiv cs.AIagentsOnline Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
arXiv:2610.39264v1 Announce Type: new Abstract: While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, small…
- arXiv cs.AIagentsMemSteer: Turning User Histories into Supervision for Agent Memory Optimization
arXiv:2610.39276v1 Announce Type: new Abstract: An effective agent memory system should adapt to a user's history and task requirements. Human-annotated supervision can guide this adaptation by providing feedback for eva…
- arXiv cs.AIagentsWhat Does "Now" Mean to Your Computer-Use Agent? Stale Screenshots, Page Loads, and Which Check to Run Before a Click
arXiv:2610.39282v1 Announce Type: new Abstract: Computer-use agents plan on a screenshot for several seconds and then click at a position on the screen; if the page has changed in the meantime, the click lands on an unin…
- arXiv cs.AIagentsBefore the Next Rollout: Diagnosing Skill Utility Shifts from Policy Updates
arXiv:2610.39358v1 Announce Type: new Abstract: Skill-evolution methods typically analyze execution trajectories to guide agent skill refinement. However, policy updates can change the behavioral effects and marginal uti…
- arXiv cs.AIagentsAgentDecept: Benchmarking Deceptive Behavior in Tool-Using LLM Agents under Pressure
arXiv:2610.39377v1 Announce Type: new Abstract: LLM agents increasingly carry out multi-turn tasks across everyday applications, yet users often see only the agent's report rather than the observations, API calls, and st…
- arXiv cs.AIagentsATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search
arXiv:2610.39438v1 Announce Type: new Abstract: Reliable local search is essential for LLM agents to support everyday decisions and longer plans by finding places that meet users' needs at given times and locations. Yet…
- arXiv cs.AIagentsDoes Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
arXiv:2610.39497v1 Announce Type: new Abstract: Progress toward artificial general intelligence (AGI) has largely relied on scaling a resource-intensive executive, System-2, through larger models, more data and compute,…
- arXiv cs.AIagentsCompile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation
arXiv:2610.39508v1 Announce Type: new Abstract: Self-evolving agent skills enable AI agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. However, s…
- arXiv cs.AIagentsFrom Intent to Improvement: Agentic Dataset Search for Better Model Training
arXiv:2610.39608v1 Announce Type: new Abstract: Finding training data in million-scale machine learning repositories is a Web search problem where text relevance is not enough. A query couples a semantic training goal wi…
- arXiv cs.AIagentsLetting AI Formulate the Research Question: Autonomous Research Agents
arXiv:2610.39620v1 Announce Type: new Abstract: Systems such as The AI Scientist have shown that AI agents can carry out and write up research, but in those demonstrations humans chose the research area and selected the…
- arXiv cs.AIagentsThe Real Cost of Context: Predicting Compute Time and Energy Consumption in LLM Prefill and Decode Phases
arXiv:2610.39621v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into agentic architectures has substantially increased token consumption, raising concerns about their energy footprint. Yet…
- arXiv cs.AIagentsMoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
arXiv:2610.39714v2 Announce Type: replace Abstract: Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecula…
- arXiv cs.AIagentsBank-World: A Benchmark for Evaluating Agents on Banking Workflows
arXiv:2610.39733v1 Announce Type: new Abstract: Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must rec…
- arXiv cs.AIagentsFinding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry
arXiv:2610.39781v1 Announce Type: new Abstract: As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes incre…
- arXiv cs.AIagentsLong-Term Agent Memory through Complementary Curation and Consolidation
arXiv:2610.39790v1 Announce Type: new Abstract: Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memor…
- arXiv cs.AIagentsEvoTeam: Multi-Agent Collaboration via Evolving Teams
arXiv:2610.39813v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills,…
- arXiv cs.AIagentsKARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents
arXiv:2610.39884v1 Announce Type: new Abstract: Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Kno…
- arXiv cs.AIagentsHuman--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration
arXiv:2610.40006v1 Announce Type: new Abstract: AI assistants are increasingly embedded in computational notebooks, scientific workflows, software engineering tools, and learning systems, yet human-AI interactions are of…
- arXiv cs.AIagentsHybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them
arXiv:2610.40036v1 Announce Type: new Abstract: Language models handle text well, and rule engines give conclusions with proofs. Systems that combine the two are usually described by example, and the same coupling turns…
- arXiv cs.AIagentsAgentic process evidence
arXiv:2610.40071v1 Announce Type: new Abstract: The way software gets built is changing dramatically. AI agents now create pull requests, select dependencies, refactor codebases, interpret test failures, and execute infr…
- arXiv cs.AIagentsDynaRev: Benchmarking Web Agents under Dynamic Goal Revision
arXiv:2610.40133v1 Announce Type: new Abstract: Web agents are typically evaluated with goals fully specified before execution and fixed thereafter, whereas real users often revise their requirements during interaction.…
- arXiv cs.AIagentsLocating and Closing Information Gaps in Multi-Agent Systems
arXiv:2610.40186v1 Announce Type: new Abstract: Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other…
- arXiv cs.AIagentsEpiAgent: Epistemic Self-Play for LLM Agents
arXiv:2610.40227v1 Announce Type: new Abstract: Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-…
- arXiv cs.AIagentsEnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation
arXiv:2610.40246v1 Announce Type: new Abstract: Computer-use agents built on large language models (LLMs) work in software that can change while they act: an appointment moves, a policy is revised, a record is updated. T…
- arXiv cs.AIagentsPrefix Executability: Evaluating Tool-Using Agents Beyond Final Success
arXiv:2610.40444v1 Announce Type: new Abstract: Tool-use benchmarks often score agents by final task success, but terminal outcomes can obscure whether the intermediate tool-call trajectory was executable. We propose pre…