AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsEvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation
arXiv:2609.01526v2 Announce Type: replace Abstract: Scientific discovery depends on the ability to form hypotheses, test them through experiments, and revise them when evidence disagrees. Existing LLM agents support this…
- arXiv cs.AIagentsFresh Memory, Stale Plans: Derivation Currency for Distributed LLM-Agent Memory
arXiv:2609.03340v2 Announce Type: replace Abstract: A large language model (LLM) agent that inherits a plan through shared memory can hold the latest requirement yet act on a plan derived from an older one: fresh memory,…
- arXiv cs.AIagentsDuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents
arXiv:2609.03423v2 Announce Type: replace Abstract: Full-duplex voice agents must continuously decide when to speak, listen, backchannel, interrupt, overlap, and yield the conversational floor. Existing benchmarks evalua…
- arXiv cs.AIagentsSciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding
arXiv:2609.05141v2 Announce Type: replace Abstract: Scientific papers require models to integrate evidence across text, equations, figures, tables, code, and datasets while preserving its provenance. Beyond answer correc…
- arXiv cs.AIagentsAgents' Overreliance on Unreliable Tools
arXiv:2609.05587v2 Announce Type: replace Abstract: LLM agents use tools to access information and perform computations beyond their parametric knowledge. Existing tool-use benchmarks evaluate whether agents select and c…
- arXiv cs.AIagentsCausalVerify: End-to-End Verification of Causal Analyses by Language Models
arXiv:2609.07944v2 Announce Type: replace Abstract: Language models increasingly perform empirical analyses end to end, yet existing evaluations assess the written explanation or whether generated code executes, not whet…
- arXiv cs.AIagentsA Theory of Reliable Self-Evolution for Agent Harnesses
arXiv:2609.08175v2 Announce Type: replace Abstract: In harness self-evolution, agents modify their own prompts, code, tools, and orchestration while keeping the underlying language model fixed. Recent work has shown that…
- arXiv cs.AIagentsDynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents
arXiv:2609.14637v3 Announce Type: replace Abstract: Large language model agents are increasingly deployed for long-horizon task execution, raising a central granularity question for trajectory evaluation: whole-trajector…
- arXiv cs.AIagentsEnabling Creative Exploration for Vibe Design Agents
arXiv:2609.15078v3 Announce Type: replace Abstract: Vibe design agents translate natural-language requests into interfaces, yet repeated generations often converge on similar visual directions. We present an inference ar…
- arXiv cs.AIagentsIssue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 Election
arXiv:2609.15207v2 Announce Type: replace Abstract: Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before elections. With grow…
- arXiv cs.AIagentsAlgoEvo: Self-Evolving Agentic Search for Automated Algorithm Discovery
arXiv:2609.15820v2 Announce Type: replace Abstract: Large language models have advanced automated algorithm discovery by synthesizing executable code, but existing frameworks trap them in rigid search pipelines with pre-…
- arXiv cs.AIagentsImproving Causal Effect Estimation of Weighted RegressionBased Estimator using Neural Networks
arXiv:2110.15075v2 Announce Type: replace-cross Abstract: Estimating causal effects from observational data informs us about which factors are important in an autonomous system, and enables us to take better decisions. T…
- arXiv cs.AIagentsMA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
arXiv:2510.16635v3 Announce Type: replace-cross Abstract: Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks tr…
- arXiv cs.AIagentsReinforcement Learning and Consumption-Savings Behavior
arXiv:2510.20748v3 Announce Type: replace-cross Abstract: This paper demonstrates how reinforcement learning can explain two puzzling empirical patterns in household consumption behavior during economic downturns. I deve…
- arXiv cs.AIagentsMitigating Hallucination in Large Language Models: A Capability-Oriented Survey on RAG, Reasoning, and Agentic Systems
arXiv:2510.24476v2 Announce Type: replace-cross Abstract: Hallucination remains one of the key obstacles to the reliable deployment of large language models (LLMs). Although various mitigation approaches have been propos…
- arXiv cs.AIagentsMASTEST: A LLM-Based Multi-Agent System For Testing RESTful APIs
arXiv:2511.18038v2 Announce Type: replace-cross Abstract: Testing RESTful API is increasingly complicated but indispensable to quality assurance of cloud-native applications. This paper reports a multi-agent system calle…
- arXiv cs.AIagentsOP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents
arXiv:2601.13722v2 Announce Type: replace-cross Abstract: Memory-augmented conversational agents enable personalized interactions using long-term user memory and have gained substantial traction. However, existing benchm…
- arXiv cs.AIagentsJust-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
arXiv:2601.18510v4 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Con…
- arXiv cs.AIagentsDr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
arXiv:2602.08847v2 Announce Type: replace-cross Abstract: Multi-agent LLM systems enable advanced reasoning and tool use via role specialization, yet reliable reinforcement learning (RL) post-training for such systems re…
- arXiv cs.AIagentsDescent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning
arXiv:2602.20078v4 Announce Type: replace-cross Abstract: Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward, each agent's learn…
- arXiv cs.AIagentsThe Trace Is the State: Exact Credit Assignment for LLM Agent Teams
arXiv:2603.06859v4 Announce Type: replace-cross Abstract: Credit assignment for a team of LLM agents, what each message was worth, has mostly been treated as prediction: a learned critic, a trajectory-level score, or an…
- arXiv cs.AIagentsDiscovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
arXiv:2603.18257v3 Announce Type: replace-cross Abstract: When an RL agent's observations contain distractors driven by the same confounders as its true state, observational data alone cannot identify which dimensions th…
- arXiv cs.AIagentsSelective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind
arXiv:2603.26089v3 Announce Type: replace-cross Abstract: The ability to represent oneself and others as agents with knowledge, intentions, and belief states that guide their behavior - Theory of Mind - is a human univer…
- arXiv cs.AIagentsMeta-TTL: Meta-Learning Self-Improvement Policies for Language Agents
arXiv:2604.00830v4 Announce Type: replace-cross Abstract: Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At…
- arXiv cs.AIagentsDeco: Extending Cherished Physical Objects into AI Companion Agents through Dual Embodiment
arXiv:2605.03882v2 Announce Type: replace-cross Abstract: Physical objects (e.g., plush toys) can transcend materiality to become emotional anchors and provide companionship. However, these bonds remain one-sided because…
- arXiv cs.AIagentsMOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
arXiv:2605.03952v2 Announce Type: replace-cross Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is str…
- arXiv cs.AIagentsEvolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
arXiv:2605.04922v2 Announce Type: replace-cross Abstract: LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically c…
- arXiv cs.AIagentsPushing the accuracy of on-top functionals with agent-driven supervised learning
arXiv:2605.06215v3 Announce Type: replace-cross Abstract: Multiconfiguration pair-density functional theory (MC-PDFT) combines multiconfigurational reference wave functions with on-top functionals to provide an efficient…
- arXiv cs.AIagentsTool Calling is Linearly Readable and Steerable in Language Models
arXiv:2605.07990v3 Announce Type: replace-cross Abstract: Language-model agents can take real actions by calling tools, so choosing the wrong tool can cause errors that are difficult to undo. Most evaluations only observ…
- arXiv cs.AIagentsAgent Collectives Should Not Detect Their Own Imposters: A Chess Case Study
arXiv:2605.09027v3 Announce Type: replace-cross Abstract: A collective of AI agents collaborating on a task has the potential to outclass any individual agent for that task. We study the robustness of such collectives ag…
- arXiv cs.AIagentsProteus: A Self-Evolving Red Team for Agent Skill Ecosystems
arXiv:2605.11891v2 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplac…
- arXiv cs.AIagentsCOTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion
arXiv:2605.15016v2 Announce Type: replace-cross Abstract: Sequential diagnosis requires ranking diseases from a sparse intake under a public budget of follow-up questions, which is diagnostic triage with missing findings…
- arXiv cs.AIagentsWho Owns This Agent? Tracing AI Agents Back to Their Owners
arXiv:2605.16035v2 Announce Type: replace-cross Abstract: AI agents increasingly act autonomously in the world, yet harmful behavior cannot be reliably traced to the account that deployed the agent. This creates an accou…
- arXiv cs.AIagentsThe End of Trust: How Agentic AI Breaks Security Assumptions
arXiv:2605.16436v2 Announce Type: replace-cross Abstract: For decades, the security of digital interaction has rested on an unacknowledged economic constraint. Attackers faced a tradeoff between the fidelity of a decepti…
- arXiv cs.AIagentsContractBench: Can LLM Agents Preserve Observation Contracts?
arXiv:2605.17281v2 Announce Type: replace-cross Abstract: Tool-augmented LLM agents call APIs whose intermediate outputs, such as presigned URLs, session tokens, and OAuth state parameters, are observation contracts: art…
- arXiv cs.AIagentsOmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments
arXiv:2605.18758v2 Announce Type: replace-cross Abstract: Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requir…
- arXiv cs.AIagentsDeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Agent Memory
arXiv:2605.22411v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents still struggle to effectively use long-term memory, with answer-supporting evidence often scattered across long conversational h…
- arXiv cs.AIagentsPhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents
arXiv:2605.29486v3 Announce Type: replace-cross Abstract: Real applications provide the training setting closest to phone-agent deployment, but are difficult to reset, scale safely, and verify programmatically. Static sc…
- arXiv cs.AIagentsMemPoison: Bypassing Selective Memory Mechanisms to Plant Backdoors in LLM Agents
arXiv:2605.29960v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly leverage long-term memory to support persistent and autonomous task execution. However, this capability also introd…
- arXiv cs.AIagentsVault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving
arXiv:2606.06219v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving must balance multimodal maneuver generation against real-time inference constraints. Diffusion planners capture diverse behaviors, b…
- arXiv cs.AIagentsAgentic Search for Counterfactual Recourse under Fixed LLM Budgets
arXiv:2606.08696v2 Announce Type: replace-cross Abstract: Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable decision made by a predictive model. In practice, affected indi…
- arXiv cs.AIagentsAgentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
arXiv:2606.10381v2 Announce Type: replace-cross Abstract: Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expan…
- arXiv cs.AIagentsLearning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
arXiv:2606.14693v2 Announce Type: replace-cross Abstract: Cooperative multi-objective multi-agent reinforcement learning (MOMARL) models team decision making under multiple, potentially conflicting objectives. In this se…
- arXiv cs.AIagentsKnowledge-Based Zero-Replay Debugging of Multi-Agent LLM Traces
arXiv:2606.14805v2 Announce Type: replace-cross Abstract: Reliable operation of multi-agent large language model (LLM) systems depends on debugging long execution traces, where the few causally decisive events are buried…
- arXiv cs.AIagentsAutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents
arXiv:2606.15057v3 Announce Type: replace-cross Abstract: Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work has proposed a variety of defensive approaches agai…
- arXiv cs.AIagentsGuava: Distilling Frontier VLMs into a Compact Agent through a Robotic Manipulation Harness
arXiv:2606.18363v3 Announce Type: replace-cross Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use o…
- arXiv cs.AIagentsCRAX: Fast Safe Reinforcement Learning Benchmarking
arXiv:2606.20376v4 Announce Type: replace-cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have bee…
- arXiv cs.AIagentsJet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
arXiv:2607.07740v4 Announce Type: replace-cross Abstract: Modern LLMs are increasingly deployed in long-context applications such as retrieval-augmented generation, repository-level coding, and agentic workflows whose ac…
- arXiv cs.AIagentsTowards Autonomous and Auditable Medical Imaging Model Development
arXiv:2607.10522v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents are beginning to automate machine learning engineering (MLE) by coupling planning, code execution, debugging, and empirical feed…
- arXiv cs.AIagentsAgent Hacks Agents: Autoresearch Discovers Vulnerabilities in Production Agents
arXiv:2607.11698v2 Announce Type: replace-cross Abstract: Production LLM agents such as Claude Code and Codex can modify files and execute commands, so safety failures become real destructive actions. Automatic red-teami…