AI news archive.
4,963 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsPrimeSeeker: Capability-Oriented Supervision for Deep Search Agents
arXiv:2609.35816v1 Announce Type: cross Abstract: Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional hops, and longer tr…
- arXiv cs.AIagents$\tau$-Multilingual: Benchmarking Voice Agents Across Languages
arXiv:2609.35820v1 Announce Type: cross Abstract: English-only benchmarks expose only a narrow slice of voice-agent behavior. We introduce $\tau$-Multilingual, extending $\tau$-Voice to Spanish, Brazilian Portuguese, Hin…
- arXiv cs.AIagentsAgentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money
arXiv:2609.35886v1 Announce Type: cross Abstract: AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the…
- arXiv cs.AIagentsSINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
arXiv:2609.35889v1 Announce Type: cross Abstract: Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effe…
- arXiv cs.AIagentsReconstructing Implicit Scientific Knowledge: Evaluating LLM Agents through End-to-End Reproduction of Astronomy
arXiv:2609.35900v1 Announce Type: cross Abstract: The integration of large language models (LLMs) into scientific workflows is accelerating, yet their ability to reconstruct the reasoning underlying published research re…
- arXiv cs.AIagentsCheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
arXiv:2609.35909v4 Announce Type: replace-cross Abstract: Autonomous LLM agents turn vulnerability discovery into a repository-scale search: they generate many vulnerability hypotheses but can verify only a subset under…
- arXiv cs.AIagentsLearn Now, Use Next, Trust Later: Prequential Test-Time Learning for LLM Agents
arXiv:2609.35911v1 Announce Type: cross Abstract: Adapting large language model agents during deployment requires not only retaining past experience, but also turning new observations into timely guidance. Many test-time…
- arXiv cs.AIagentsMMSkillRisk: Can Agents Stay Safe When Multimodal Skills Become Traps?
arXiv:2609.35912v1 Announce Type: cross Abstract: Agent skills are shareable packages of procedural instructions, tools, and examples. Multimodal skills additionally include visual references that agents retrieve and ins…
- arXiv cs.AIagentsEvaluating Name-Only Directory Routing for One-Shot Code Search
arXiv:2609.35918v1 Announce Type: cross Abstract: Finding the right files is an early challenge for coding agents. We test whether a language model can follow directory and file names to find annotated code files missed…
- arXiv cs.AIagentsAlmost Human, Except When It Matters: VoxParity and the Decisions a Voice Should Change
arXiv:2609.35922v1 Announce Type: cross Abstract: A voice agent can handle almost every call on the words alone and still fail the few its sector's rules were written for. Emergency-call standards, fraud guidance, radio…
- arXiv cs.AIagentsPrompted Identity Degrades Cooperation in Multi-Agent LLM Systems
arXiv:2609.35928v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation…
- arXiv cs.AIagentsSame Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection
arXiv:2609.35932v1 Announce Type: cross Abstract: Prompt injection against LLM agents becomes much stronger when the injected instruction is wrapped in the model's own chat template. A forged template marker such as can…
- arXiv cs.AIagentsEmbodied Semantic Communication for Collective Autonomous Agents: A Tutorial on Representation, Wireless Delivery, and Closed-Loop Coordination
arXiv:2609.35936v1 Announce Type: cross Abstract: As autonomous systems and embodied intelligence enter the dynamic physical world, multi-agent collaboration calls for a paradigm shift in communication design. However, e…
- arXiv cs.AIagentsPrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents
arXiv:2609.35937v1 Announce Type: cross Abstract: While prior work has documented privacy failures in LLM agents, it remains unclear how the presentation of privacy guidance influences their choice of information sources…
- arXiv cs.AIagentsSolver Agent: an Agentic AI Framework for Theoretical Physics Computations Applied to F-theory Uplifts of O3-planes and S-folds
arXiv:2609.35958v1 Announce Type: cross Abstract: We introduce Solver Agent, an AI framework based on large language models for calculations and proofs in mathematics and theoretical physics. The solution process is trac…
- arXiv cs.AIagentsSystematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method
arXiv:2609.35965v2 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) has largely focused on a single agent following a single instruction, yet many real-world applications require teams of robot…
- arXiv cs.AIagentsMnemon: Raw Records, Fast Judgments, Slow Thoughts
arXiv:2609.36059v1 Announce Type: cross Abstract: Long-term memory lets an LLM assistant use a history it can no longer reread, and most memory systems build it by rewriting conversations into facts, graphs or typed memo…
- arXiv cs.AIagentsAerialDojo-200K: A Large-Scale Benchmark Suite for Open-World Aerial Object-Goal Search
arXiv:2609.36066v1 Announce Type: cross Abstract: Open-world aerial object-goal search is a foundational yet challenging task, requiring aerial agents to autonomously explore large-scale, unstructured three-dimensional e…
- arXiv cs.AIagentsPADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators
arXiv:2609.36086v1 Announce Type: cross Abstract: Language models are frequently employed to evaluate other language models. An LM evaluator scoring agentic behaviors across multiple criteria is valuable, provided that i…
- arXiv cs.AIagentsLanguage Models Are "Insecure" Reporters
arXiv:2609.36139v1 Announce Type: cross Abstract: As large language models are deployed in increasingly autonomous long-horizon tasks, manually auditing and verifying the actions, artifacts, and outputs of models becomes…
- arXiv cs.AIagentsFrom Dead Code and Static Requirements to Working Engines: Software Revival with Coding Agents
arXiv:2609.36161v1 Announce Type: cross Abstract: Can coding agents restore software that no longer runs while preserving its underlying methods, and reconstruct industrial software engines from open specifications? Here…
- arXiv cs.AIagentsTargeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment of trajectory-level ad…
- arXiv cs.AIagentsSCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety
arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under benign instructions an…
- arXiv cs.AIagentsLatentSift: Policy-State Filtering for Token-Efficient Verification of Software Engineering Agents
arXiv:2609.36371v1 Announce Type: cross Abstract: Test-time scaling improves software engineering agents by generating multiple candidate trajectories and selecting the best one. Verifying and selecting among these long…
- arXiv cs.AIagentsAudience-Bound Persistent Memory: Authorization Across the Memory Lifecycle
arXiv:2609.36373v1 Announce Type: cross Abstract: A personal language agent that acts for its owner across private and shared conversations can learn a fact from one audience and later place it in the context it assemble…
- arXiv cs.AIagentsReward-rate Policy Gradient for Efficient Machine Learning Engineering Agents
arXiv:2609.36393v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit of time. However, thi…
- arXiv cs.AIagentsLLMs Learn to Evade Latent Monitors from Prior Feedback Alone
arXiv:2609.36490v1 Announce Type: cross Abstract: Latent space monitors aim to detect undesired behaviors in LLM agents by inspecting an agent's internal activations rather than its outputs. However, interactive monitori…
- arXiv cs.AIagentsAdapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
arXiv:2609.36526v1 Announce Type: cross Abstract: Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. E…
- arXiv cs.AIagentsCounterSteer: Suppressing Indirect Prompt Injection with Activation Steering
arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that suppresses this behav…
- arXiv cs.AIagentsCooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning
arXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLAs are pretrained on l…
- arXiv cs.AIagentsText2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise
arXiv:2609.36593v2 Announce Type: replace-cross Abstract: Creating diverse physical simulations remains labor-intensive because assets, layout, physical parameters, motion, control, and rendering must be designed and deb…
- arXiv cs.AIagentsSimple Agentic Memory for Generalist Robot Policies
arXiv:2609.36595v1 Announce Type: cross Abstract: Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly…
- arXiv cs.AIagentsWitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses
arXiv:2609.36635v1 Announce Type: cross Abstract: Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness and exposes faulty be…
- arXiv cs.AIagentsFrontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change
arXiv:2609.36739v1 Announce Type: cross Abstract: Multi-agent LLM systems are increasingly structured like organizations, with roles, critics and shared memory, yet they are evaluated on tasks that last minutes. We ask h…
- arXiv cs.AIagentsOn-Policy Visual Evidence Distillation
arXiv:2609.36838v1 Announce Type: cross Abstract: Visual agents solve problems by interleaving reasoning with image operations, and on-policy distillation (OPD) provides guidance from a strong teacher on student-generate…
- arXiv cs.AIagentsDoes the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
arXiv:2609.36849v1 Announce Type: cross Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single p…
- arXiv cs.AIagentsSKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
arXiv:2609.36879v1 Announce Type: cross Abstract: As LLM-based agents perform increasingly complex tasks, Agent Skills have emerged as a flexible mechanism for extending their capabilities. An Agent Skill packages task-s…
- arXiv cs.AIagentsFACT: Fidelity-Aware Construction of Articulated Twins
arXiv:2609.37067v2 Announce Type: replace-cross Abstract: Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Art…
- arXiv cs.AIagentsVACE: Validation-Gated Alternating Co-Evolution of Agent Models and Harnesses
arXiv:2609.37105v1 Announce Type: cross Abstract: Language model agents can be improved by updating their model weights or refining the harness that guides task execution. These components are coupled: weight updates cha…
- arXiv cs.AIagentsLucid Dreaming for World Models: Learning to Doubt Imagination and Decide by Trust
arXiv:2609.37156v1 Announce Type: cross Abstract: World models enable agents to learn and plan in imagination, but predictions beyond their experience can become unreliable and mislead decisions. Existing uncertainty est…
- arXiv cs.AIagentsToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents
arXiv:2609.37196v1 Announce Type: cross Abstract: Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content…
- arXiv cs.AIagentsFollow the Entities: A Corpus Map for Agentic Search
arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as a project's approval…
- arXiv cs.AIagentsDo Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments
arXiv:2609.37315v1 Announce Type: cross Abstract: Tool-using agents are entering settings where a wrong action carries real cost, and the benchmarks certifying them grade what each simulated tool call reports having done…
- arXiv cs.AIagentsPowerMarketJax: A JAX Benchmark Suite for Multi-Agent Reinforcement Learning in Power Markets
arXiv:2609.37321v1 Announce Type: cross Abstract: Power markets are a natural testbed for multi-agent reinforcement learning (MARL), where multiple self-interested participants repeatedly submit bids. A market-clearing m…
- arXiv cs.AIagentsEncore: Few-Shot Agentic Discovery of Manipulation Strategies
arXiv:2609.37359v1 Announce Type: cross Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in wh…
- arXiv cs.AIagentsBackdoor in the Loop: Compromising Agentic Search via Malicious Retrievers
arXiv:2609.37468v1 Announce Type: cross Abstract: Agentic retrieval-augmented generation (RAG) interleaves reasoning with repeated retrieval, giving the retriever influence over both the evidence an agent observes and it…
- arXiv cs.AIagentsEvaluating Bounded Autonomy in Regulated Agentic AI: A Diagnostic Harness with Constitutional Rewards, Escalation Labels, and Runtime Governance
arXiv:2609.37501v1 Announce Type: cross Abstract: We propose RegLLM, a diagnostic harness for bounded autonomy in regulated agentic workflows. It instruments six trustworthiness signals: citation validity, source groundi…
- arXiv cs.AIagentsConcealing LLM-Based Multi-Agent Topology via Phantom Structure Injection
arXiv:2609.37567v1 Announce Type: cross Abstract: Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collaborative reasoning over…
- arXiv cs.AIagentsRLTLDR: Self-improvement by Internalizing Self-generated Feedback
arXiv:2609.37633v2 Announce Type: replace-cross Abstract: The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successfu…
- arXiv cs.AIagentsA Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
arXiv:2609.37783v1 Announce Type: cross Abstract: Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to eval…