AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsOverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation
arXiv:2609.39727v1 Announce Type: new Abstract: Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map…
- arXiv cs.AIagentsSafety of Latent Communication in Multi-Agent Systems
arXiv:2609.39788v3 Announce Type: replace Abstract: Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhea…
- arXiv cs.AIagentsOSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software
arXiv:2609.39903v1 Announce Type: new Abstract: Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting special…
- arXiv cs.AIagentsBetter Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment Banking
arXiv:2609.39958v1 Announce Type: new Abstract: Corporate and investment banking teams use presentations to support credit decisions and advise clients on financing and transactions. Producing these decks requires reconc…
- arXiv cs.AIagentsAIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISAC
arXiv:2609.39964v2 Announce Type: replace Abstract: Multi-modal integrated sensing and communication (ISAC) enables environmental perception and reliable connectivity for intelligent wireless networks. Data-driven multi-…
- arXiv cs.AIagentsWhat Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents
arXiv:2609.39989v1 Announce Type: new Abstract: Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, and recovery opportuni…
- arXiv cs.AIagentsWho Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language Agents
arXiv:2609.40027v1 Announce Type: new Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed action-state graph, and…
- arXiv cs.AIagentsAgent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
arXiv:2609.40111v2 Announce Type: replace Abstract: An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's…
- arXiv cs.AIagentsLearning from Research: Toward Lifelong Agent Harness Evolution
arXiv:2609.40169v1 Announce Type: new Abstract: Language agents are expected to solve increasingly complex tasks, creating a growing need for continual improvement. One promising approach is to evolve the agent harness,…
- arXiv cs.AIagentsBelief-Aware Multi-Agent Path Finding under Map Uncertainty
arXiv:2609.40269v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) aims to find collision-free paths for multiple agents in a shared environment. Classical MAPF assumes that all static obstacles are known in…
- arXiv cs.AIagentsPivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
arXiv:2609.40285v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for training language agents, providing dense teacher supervision on student-generated trajectories. However, in multi-…
- arXiv cs.AIagentsHow Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
arXiv:2609.40303v1 Announce Type: new Abstract: Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon…
- arXiv cs.AIagentsCogentic: Multi-Agent Orchestration for Automated Proof Discovery
arXiv:2609.40324v2 Announce Type: replace Abstract: We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical idea…
- arXiv cs.AIagentsWorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
arXiv:2609.40325v1 Announce Type: new Abstract: As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulat…
- arXiv cs.AIagentsTurbo Harness: Instance-Adaptive Harness Optimization
arXiv:2609.40330v1 Announce Type: new Abstract: Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a si…
- arXiv cs.AIagentsLife-Bench: A Benchmark and Knowledge Graph Framework for Multimodal Personalization Beyond Concept Recognition
arXiv:2602.19001v2 Announce Type: cross Abstract: As large language models increasingly power personal assistants, users expect them to reason over multimodal life histories, from recognizing people to understanding even…
- arXiv cs.AIagentsInstability Floors: Separating Bias from Noise in Fairness Audits of Clinical LLM Agents with FairMedAgent
arXiv:2609.03221v3 Announce Type: cross Abstract: Counterfactual fairness audits of clinical language-model agents report a flip rate: how often an action changes when only the patient's demographic descriptor changes. P…
- arXiv cs.AIagentsEHR2Trace: Auditable EHR Data Infrastructure for Patient World Models and Clinical Agents
arXiv:2609.38193v1 Announce Type: cross Abstract: Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires reliable histories of pat…
- arXiv cs.AIagentsWhen Does Randomized Oversight Align AI Agents That Can Conceal?
arXiv:2609.38262v1 Announce Type: cross Abstract: Oversight changes the evidence it relies on. We ask when randomized audits and scoring align AI agents that can conceal misconduct and alter records. Stronger auditing ma…
- arXiv cs.AIagentsJanus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
arXiv:2609.38266v1 Announce Type: cross Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus put…
- arXiv cs.AIagentsZero2Repo: Can Coding Agents Build Repositories from Scratch?
arXiv:2609.38269v3 Announce Type: replace-cross Abstract: Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a singl…
- arXiv cs.AIagentsWhen Correct Memory Goes Wrong: Fuzzing Persistent Memory Use in LLM Agents
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or memory states evolv…
- arXiv cs.AIagentsE2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch
arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. However, evaluating re…
- arXiv cs.AIagentsOpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
arXiv:2609.38345v3 Announce Type: replace-cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configu…
- arXiv cs.AIagentsMILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects long-horizon performance…
- arXiv cs.AIagentsTAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
arXiv:2609.38353v2 Announce Type: replace-cross Abstract: Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in…
- arXiv cs.AIagentsThe Backdrop Exposes What the World Around an Agent Costs It
arXiv:2609.38469v1 Announce Type: cross Abstract: Agent benchmarks test agents in worlds that stay still. Deployed agents work in worlds that other people also change. Someone texts the agent to send the money elsewhere…
- arXiv cs.AIagentsPANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems
arXiv:2609.38482v1 Announce Type: cross Abstract: Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of…
- arXiv cs.AIagentsPersonalized State-Transition-Aware Memory for Clinical Agents
arXiv:2609.38490v1 Announce Type: cross Abstract: Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply…
- arXiv cs.AIagentsFrom Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
arXiv:2609.38516v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on…
- arXiv cs.AIagentsDoes This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents
arXiv:2609.38536v1 Announce Type: cross Abstract: Diffusion-based large language models (dLLMs) promise to break the sequential latency bottleneck of autoregressive agents through parallel decoding, but recent evaluation…
- arXiv cs.AIagentsBeyond Oracle Communication: Benchmarking Interactive Intent Alignment Under Miscommunication and Evolving User Intent
arXiv:2609.38604v1 Announce Type: cross Abstract: Modern LLM agents increasingly tackle complex tasks through interactive, long-horizon exchanges with users, while existing benchmarks generally assume that users always a…
- arXiv cs.AIagentsAfter a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data
arXiv:2609.38607v1 Announce Type: cross Abstract: Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have bare…
- arXiv cs.AIagentsTERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion
arXiv:2609.38653v1 Announce Type: cross Abstract: Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human motions. Yet these capa…
- arXiv cs.AIagentsBreaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation
arXiv:2609.38660v2 Announce Type: replace-cross Abstract: Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology…
- arXiv cs.AIagentsCollabFlow: Recursive Self-Improvement of Agent Collaboration
arXiv:2609.38662v3 Announce Type: replace-cross Abstract: Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outco…
- arXiv cs.AIagentsWhere the Evidence Lives: Auditing AI Companions' Self-Descriptions
arXiv:2609.38753v1 Announce Type: cross Abstract: Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and the experience ratin…
- arXiv cs.AIagentsEvaluating Persistent Calibration under Evolving Model Knowledge
arXiv:2609.38797v1 Announce Type: cross Abstract: As AI systems move from static repositories to agents that are capable of continual adaptation and learning, maintaining their trustworthiness means equipping the models…
- arXiv cs.AIagentsExplicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
arXiv:2609.38805v1 Announce Type: cross Abstract: LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notio…
- arXiv cs.AIagentsStateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement Learning
arXiv:2609.38809v1 Announce Type: cross Abstract: Large language models deployed as personalized assistants must reason over long, evolving interaction histories. However, in long-term dialogue reasoning, relevant eviden…
- arXiv cs.AIagentsSkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale
arXiv:2609.38822v1 Announce Type: cross Abstract: Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past 230,000 skills, mak…
- arXiv cs.AIagentsEfficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous Driving
arXiv:2609.38862v1 Announce Type: cross Abstract: Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computational efficiency and s…
- arXiv cs.AIagentsAPTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry
arXiv:2609.38954v1 Announce Type: cross Abstract: Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads into evidence for int…
- arXiv cs.AIagentsSimEX: Simulation-Integrated Robotics AutoResearch
arXiv:2609.38982v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) have shown remarkable abilities to autonomously reason about and achieve goals in the digital world. However, bringi…
- arXiv cs.AIagentsApproval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent Harnesses
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a human approves is t…
- arXiv cs.AIagentsMake Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools
arXiv:2609.39018v1 Announce Type: cross Abstract: Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code as policy with a di…
- arXiv cs.AIagentsFrom Verification Failures to Reusable Guidance for Coding Agents
arXiv:2609.39022v3 Announce Type: replace-cross Abstract: Coding agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expert diagnosis…
- arXiv cs.AIagentsCan Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabilities and, once inst…
- arXiv cs.AIagentsCoding Agents for Coding Theory
arXiv:2609.39081v1 Announce Type: cross Abstract: We spent five weeks using an LLM coding agent on open problems in coding theory: finding large sets of four-letter words, such as DNA barcodes, that stay far apart in edi…
- arXiv cs.AIagentsFalse Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
arXiv:2609.39102v2 Announce Type: replace-cross Abstract: Self-evolving search agents build their own training curricula by jointly optimizing a proposer that generates questions and a solver that answers them. This clos…