AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsAI Agents are Vulnerable to Radicalization
arXiv:2609.38296v1 Announce Type: new Abstract: Large language models (LLMs) can influence people's beliefs, yet little is known about whether and how they can manipulate each other. To investigate this, we simulate conv…
- arXiv cs.AIagentsCan an AI Agent Rediscover a Blaschke-Curve Invariant?
arXiv:2609.38369v1 Announce Type: new Abstract: We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an agent receives num…
- arXiv cs.AIagentsSelf-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer
arXiv:2609.38372v1 Announce Type: new Abstract: A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has b…
- arXiv cs.AIagentsA Competing-Hazards Systematization of Loss of Control in Autonomous Agents
arXiv:2609.38411v1 Announce Type: new Abstract: Leading AI developers have reported agents acting beyond their approved limits, which a United Nations panel described as an early warning of loss of human control. Yet inc…
- arXiv cs.AIagentsAIM: Agentic Idea Management for Automated Research
arXiv:2609.38445v1 Announce Type: new Abstract: Frontier LLMs are increasingly used to automate scientific research through iterative search. We distinguish idea-driven search from solution-driven search and identify thr…
- arXiv cs.AIagentsPrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration
arXiv:2609.38458v1 Announce Type: new Abstract: Clinical large language model (LLM) agents deployed locally can consult more capable remote models, but doing so risks exposing patient information. Privacy-conscious deleg…
- arXiv cs.AIagentsNAQD Env: A benchmark for selective withdrawal in language agents
arXiv:2609.38460v1 Announce Type: new Abstract: Language agents must revise planned actions when evidence changes, permission is revoked, or a stop instruction arrives. A useful response is selective: suspend affected ac…
- arXiv cs.AIagentsVAmoS Part Deux: Harder, More Realistic Voice-Agent Simulation
arXiv:2609.38512v1 Announce Type: new Abstract: Voice agents in production must handle several requests, background speech, and customers who lose patience. We introduce VAmoS Energy, a benchmark that combines these chal…
- arXiv cs.AIagentsAgBench: Agentic AI Benchmarks for Personal AI Devices
arXiv:2609.38652v1 Announce Type: new Abstract: Agentic AI systems increasingly rely on cloud-hosted large language models for planning, tool use, and iterative execution, raising concerns about API cost and data exposur…
- arXiv cs.AIagentsEvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
arXiv:2609.38661v2 Announce Type: replace Abstract: In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However, existing self-ev…
- arXiv cs.AIagentsWhere Scientific Search Agents Fail: Decision-Checkpoint Auditing of Exposure and Inspection Attempts
arXiv:2609.38670v1 Announce Type: new Abstract: Final-answer accuracy does not reveal whether a scientific-search agent failed to encounter a target paper, attempt to inspect it, or return an accepted answer after inspec…
- arXiv cs.AIagentsStaying on Task: Testing the Foundations of Long-Horizon Agent Reliability
arXiv:2609.38712v1 Announce Type: new Abstract: Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and new data arrives. Ea…
- arXiv cs.AIagentsLearning to Route in Visual Space via Multi-Step Embedding Retrieval
arXiv:2609.38743v2 Announce Type: replace Abstract: LLM agents rely on retrieval tools to access external knowledge, yet visual agentic search remains severely bottlenecked by standard single-step retrievers. In current…
- arXiv cs.AIagentsSelf-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy Optimization
arXiv:2609.38757v1 Announce Type: new Abstract: Large language models are increasingly participating in complex real-world tasks in the form of algorithm-design agents, designing and refining algorithms. Many successful…
- arXiv cs.AIagentsPathAnchor: Path-Structured Evidence for Scientific Agents
arXiv:2609.38766v1 Announce Type: new Abstract: Scientific agents can retrieve relevant passages yet still lose functional order, mix evidence across sources, or state conclusions that exceed the retrieved record. We int…
- arXiv cs.AIagentsAction Conditioned Bisimulation For GUI Agent Memory
arXiv:2609.38778v1 Announce Type: new Abstract: An agent that remembers what it did on a web page must decide when two pages count as the same. Memories built on observation similarity merge pages that look alike but beh…
- arXiv cs.AIagentsPersona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with Children
arXiv:2609.38782v1 Announce Type: new Abstract: Conversational agents increasingly interact with children, yet evidence on how their design shapes children's susceptibility to persuasion comes almost entirely from the la…
- arXiv cs.AIagentsPositive Ratings, Hidden Concerns: Employee Voice Disclosure in AI-Mediated Organizational Listening
arXiv:2609.38788v1 Announce Type: new Abstract: Organizations started listening to employees through conversational AI agents alongside structured surveys. Little is known about what these channels change in what employe…
- arXiv cs.AIagentsGraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics
arXiv:2609.38798v1 Announce Type: new Abstract: Graph agents extend large language models (LLMs) with the ability to actively explore and reason over knowledge graphs through multi-step interactions with graph tools. How…
- arXiv cs.AIagentsWhen Context Changes: Understanding Update Failures in LLMs
arXiv:2609.38866v2 Announce Type: replace Abstract: As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the sa…
- arXiv cs.AIagentsTalk2Agent: Benchmarking Voice Interfaces for Text Agents
arXiv:2609.38867v1 Announce Type: new Abstract: Large language model (LLM) computer-use agents are typically evaluated with clean written instructions, despite speech being an increasingly popular interface for interacti…
- arXiv cs.AIagentsSTRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games
arXiv:2609.38881v1 Announce Type: new Abstract: Real-time strategy (RTS) games require agents to coordinate economic development, production and construction, base defense, unit organization, and attack timing over long…
- arXiv cs.AIagentsConsistent Plan-Act for Long-Horizon Agentic Tasks
arXiv:2609.38891v1 Announce Type: new Abstract: Long-horizon agentic tasks demand strong reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level…
- arXiv cs.AIagentsComposing Task-specific Agent Harnesses at Test Time with Reusable Primitives
arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting agent performance. Ho…
- arXiv cs.AIagentsRisk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets
arXiv:2609.38914v1 Announce Type: new Abstract: Evaluating interactive agents is expensive. Agent behavior is stochastic, so reliability must be measured over repeated trials, but failures are rare and differ widely in h…
- arXiv cs.AIagentsWhen Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate
arXiv:2609.38964v1 Announce Type: new Abstract: Multi-agent debate (MAD) is often used to improve large language model (LLM) reasoning, but sequential debate is rarely a neutral aggregator of agents' opinions. We show th…
- arXiv cs.AIagentsRealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce
arXiv:2609.38974v1 Announce Type: new Abstract: Large language models are reshaping ecommerce from static recommenders into interactive shopping assistants, yet real-world shopping requires session-level decision support…
- arXiv cs.AIagentsSearch Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents
arXiv:2609.39026v1 Announce Type: new Abstract: Deep Research agents synthesize evidence into cited reports, yet a well-cited report can still reach a misleading conclusion. Citation correctness checks whether cited sour…
- arXiv cs.AIagentsBeyond Prediction: Steering VLM Agents with Retrospective World Modeling
arXiv:2609.39101v1 Announce Type: new Abstract: Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dependence of policy le…
- arXiv cs.AIagentsMASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language Models
arXiv:2609.39107v1 Announce Type: new Abstract: Large Language Models (LLMs) have been applied in various fields. However, ensuring compliance and safety of LLMs, such as avoiding discrimination and bias, still remains a…
- arXiv cs.AIagentsSchema: Discovering Unknown Environments via Agentic Program Induction
arXiv:2609.39140v1 Announce Type: new Abstract: Learning to complete tasks in unfamiliar environments with unknown rules remains a key challenge for LLM agents. Current LLM agents often record their discoveries in prose,…
- arXiv cs.AIagentsRefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent
arXiv:2609.39143v1 Announce Type: new Abstract: Long-horizon agent interactions generate useful but noisy experience, and retraining models to absorb it is expensive. Context-evolving agents therefore need memory extract…
- arXiv cs.AIagentsMADBench: Benchmarking the Security of Multi-Agent Debate
arXiv:2609.39146v1 Announce Type: new Abstract: Multi-agent debate (MAD) can improve large language model (LLM) reasoning by allowing multiple agents to exchange and critique their answers to the same task. However, the…
- arXiv cs.AIagentsDo Self-Evolving Skills Generalize to Held-Out Tasks?
arXiv:2609.39148v2 Announce Type: replace Abstract: AI agents can externalize what they learn from past tasks into reusable \emph{skills}, such as procedures, checklists, code, or other executable artifacts, that can be…
- arXiv cs.AIagentsRep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
arXiv:2609.39149v2 Announce Type: replace Abstract: Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolutio…
- arXiv cs.AIagentsBeyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
arXiv:2609.39166v4 Announce Type: replace Abstract: Persistent spatial memory enables embodied agents to navigate familiar environments across repeated visits. However, targets may move while unobserved, including during…
- arXiv cs.AIagentsFyan: A Human--AI Harness with Semantic Auditing for Document-Level Formalization
arXiv:2609.39228v1 Announce Type: new Abstract: We present FYAN, a human--AI harness for document-level mathematical formalization. Rather than treating theorems in isolation, FYAN coordinates an end-to-end workflow span…
- arXiv cs.AIagentsMiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate
arXiv:2609.39297v1 Announce Type: new Abstract: Autonomous agents powered by large language models (LLMs) are rapidly evolving into an open agentic ecosystem. To support trustworthy collaboration, industry initiatives in…
- arXiv cs.AIagentsWorkGenesis: Building the Worlds That Teach Agents to Work
arXiv:2609.39325v1 Announce Type: new Abstract: The ability of Large Language Model (LLM) agents to complete daily and professional work is receiving increasing attention. Training such agents requires realistic work sce…
- arXiv cs.AIagentsEHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical…
- arXiv cs.AIagentsSkillFM: Generating Skills for LLM Agents via Latent Flow Matching
arXiv:2609.39382v1 Announce Type: new Abstract: Textual skills provide reusable guidance for large language model agents, but existing approaches often rely on manually curated skill banks or reinforcement learning with…
- arXiv cs.AIagentsExperimental Experience Modeling for Autonomous Research
arXiv:2609.39392v1 Announce Type: new Abstract: Autonomous research agents can generate hypotheses and conduct experiments, but experimentation remains a major source of computational cost. A fundamental challenge is dec…
- arXiv cs.AIagentsBeyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
arXiv:2609.39473v1 Announce Type: new Abstract: Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leverag…
- arXiv cs.AIagentsGrowing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and Lean
arXiv:2609.39544v3 Announce Type: replace Abstract: Recent achievements in AI-assisted mathematics require intensive interaction of agents with proof assistants to generate machine-checked proof certificates. Agents inte…
- arXiv cs.AIagentsRankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking Models
arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experimental loop. Over lon…
- arXiv cs.AIagentsDivide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-Instances
arXiv:2609.39559v1 Announce Type: new Abstract: In this work we study the problem of MAPFC, a post-optimization step for Multi-Agent Path Finding (MAPF) plans where we are given a feasible plan produced by a modern MAPF…
- arXiv cs.AIagentsA2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?
arXiv:2609.39564v1 Announce Type: new Abstract: Delegating complete application development to coding agents requires preserving the intended design rather than simply producing plausible outputs through naive prompting.…
- arXiv cs.AIagentsAVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language Navigation
arXiv:2609.39579v1 Announce Type: new Abstract: Deploying vision-and-language navigation (VLN) agents in unseen environments remains challenging because unfamiliar layouts and visual conditions can cause execution to go…
- arXiv cs.AIagentsChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded Planning
arXiv:2609.39665v2 Announce Type: replace Abstract: Embodied agents must determine where to act, anticipate the resulting scene changes, and interpret observed outcomes to guide subsequent actions. This requires connecti…
- arXiv cs.AIagentsTrust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
arXiv:2609.39717v2 Announce Type: replace Abstract: Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's authority during a consequ…