AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- SiliconANGLE AIagentsStartup Action State launches tools for verifying interactions between AI agents
Action State Group Inc. is launching a set of open-source tools designed to let businesses independently check records of what artificial intelligence agents did, addressing a trust problem as automated systems begin buy…
- The DecoderagentsAn AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
Security researchers at Symantec have found an offensive AI agent that hijacks unprotected language models on the web and uses them to attack servers, steal databases, and install cryptominers on its own. It runs up to 1…
- Tom's Guide AIagentsDitch the data center: I fired my cloud chatbot and built a free local AI agent to run on my PC — and you can too
Consumer AI launches, tools, and practical coverage.
- TechRadar AIagentsCould AI agents be causing surprise bills at your business? You're not alone
Mainstream AI news from a large tech publication.
- The DecoderagentsOpenAI agents analyze mouse brain data in 32 minutes, a job that would take humans months
OpenAI teamed up with PerturbAI and Scripps Research to deploy thousands of AI agents that analyzed biological data from millions of mouse cells. The article OpenAI agents analyze mouse brain data in 32 minutes, a job th…
- The Verge AIagents1Password lets AI agents use your passwords without seeing them
1Password is introducing a new feature that allows AI agents to sign into your accounts without actually seeing or handling your passwords. The aptly named 1Password for Agents doesn't give bots free reign to access all…
- The DecoderagentsAnthropic takes on Grok Bot, Meta's Muse, and OpenAI's Dots with its always-on agent "Claude Duet"
Anthropic has launched Claude Duet, a proactive AI agent that handles tasks on its own, even when the user is offline. The app is built on Claude Opus 5.5 and connects to services like Gmail, Slack, and Stripe through mo…
- Tom's Guide AIagentsOpenAI unleashed thousands of AI agents to study a Parkinson-like disease — here's what they found in 32 minutes
Consumer AI launches, tools, and practical coverage.
- Engadget AIagents1Password will let Muse, Dots and Grok Bot sign in to sites for you without getting your credentials
If you're willing to let AI book or buy things on your behalf, 1Password just made that easier.
- arXiv cs.AIagentsScaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds
arXiv:2610.28698v1 Announce Type: new Abstract: Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared physical laws. Wheth…
- arXiv cs.AIagentsAutomating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?
arXiv:2610.28763v1 Announce Type: new Abstract: Frontier coding agents are increasingly framed as end-to-end automated researchers, and ML for science offers a demanding test of that promise: improving a scientific model…
- arXiv cs.AIagentsForging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing
arXiv:2610.28815v1 Announce Type: new Abstract: Agentic harness evolution optimizes an agent's instructions, tools, and control flow by using its task execution experiences as evolving evidence. While more evolution task…
- arXiv cs.AIagentsFig: Automated Multiagent Behavior Elicitor
arXiv:2610.28891v2 Announce Type: replace Abstract: Many social evaluations for multiagent systems study behaviors as they emerge from environments instead of systematically intervening in the environment to elicit such…
- arXiv cs.AIagentsHidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent Communication
arXiv:2610.28905v1 Announce Type: new Abstract: Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate o…
- arXiv cs.AIagentsD-Skill: Distilling Teacher Knowledge through Agent Skills
arXiv:2610.28914v1 Announce Type: new Abstract: Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge dist…
- arXiv cs.AIagentsBack Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding Agents
arXiv:2610.28934v1 Announce Type: new Abstract: Coding agents now complete tasks autonomously, modifying real-world state such as artifacts, software environments, and configurations along the way. Yet they show limited…
- arXiv cs.AIagentsSelf-Improving Agents with World Model Predictive Paths
arXiv:2610.28945v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to interact with environments and improve their decisions during deployment. However, how anticipating future ou…
- arXiv cs.AIagentsBehavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
arXiv:2610.28982v1 Announce Type: new Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in…
- arXiv cs.AIagentsPerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
arXiv:2610.28987v1 Announce Type: new Abstract: Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architectur…
- arXiv cs.AIagentsAgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards
arXiv:2610.28989v1 Announce Type: new Abstract: Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies in the task agent's prompt does not reliably prevent…
- arXiv cs.AIagentsAn Evidence-Driven Multi-Agent Compound AI System for Head and Neck Proton Radiotherapy Planning
arXiv:2610.29010v1 Announce Type: new Abstract: Radiation treatment planning requires balancing competing objectives to satisfy clinical criteria while accommodating physicians' preferences. This study aims to develop an…
- arXiv cs.AIagentsGenXR-Bench: Benchmarking Coding Agents for Interactive XR Development
arXiv:2610.29014v2 Announce Type: replace Abstract: Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interac…
- arXiv cs.AIagentsInheritance as an Admission Test for LLM Prompt Merge Operators
arXiv:2610.29023v1 Announce Type: new Abstract: Large language model (LLM) agents are often improved by iterating until a fixed verifier is done. Once that verifier saturates, the loop has nothing left to climb. We inste…
- arXiv cs.AIagentsRecursive Self-Improvement on a Budget: Scoring Code Edits Before They Run
arXiv:2610.29121v1 Announce Type: new Abstract: A coding agent that rewrites its own scaffold has to choose which proposed edit to expand before that edit has been evaluated, and the search then has to return one agent.…
- arXiv cs.AIagentsLaVGuard: Selective Decoding for Contextual Value Drift
arXiv:2610.29135v1 Announce Type: new Abstract: A content-safe response can still promote priorities that conflict with its task: an assistant may demand compliance when asked to preserve autonomy. We study contextual va…
- arXiv cs.AIagentsSteering Black-Box Large Language Model Agents with Pitfall Anticipation World Model
arXiv:2610.29139v1 Announce Type: new Abstract: Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic ta…
- arXiv cs.AIagentsCrashGym: Measuring the Decision Value of Experimentation for LLM Agents in Counterfactual Market Crashes
arXiv:2610.29245v1 Announce Type: new Abstract: Language-model agents are increasingly asked to run experiments, yet benchmarks rarely measure whether those experiments improve the decisions they are meant to inform. We…
- arXiv cs.AIagentsAgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents
arXiv:2610.29330v2 Announce Type: replace Abstract: How do LLM agents' strategies differ, and how much can instructions to adopt a persona change their behavior over a game? We study these questions with AgentMonopoly, a…
- arXiv cs.AIagentsFrom Prompts to Posteriors: Can LLM Agents Perform Bayesian Inference in Context?
arXiv:2610.29331v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly applied across the scientific discovery pipeline, from synthesizing literature to generating hypotheses to informing experimen…
- arXiv cs.AIagentsPreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents
arXiv:2610.29467v1 Announce Type: new Abstract: Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often appe…
- arXiv cs.AIagentsReal PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents
arXiv:2610.29812v1 Announce Type: new Abstract: Literature-searching language agents are becoming a standard component of scientific assistants for the life sciences, yet there is little controlled evidence on which part…
- arXiv cs.AIagentsUserSWE: Evaluating Coding Agents in Multi-Turn Conversations with Dynamic Users
arXiv:2610.29822v1 Announce Type: new Abstract: As coding agents become more capable, developers increasingly use them to fix bugs through multi-turn interactions. Existing benchmarks do not adequately cover this scenari…
- arXiv cs.AIagentsToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination
arXiv:2610.29934v1 Announce Type: new Abstract: Forming an accurate theory-of-mind (ToM) is key to successful multi-agent collaboration and requires reasoning under uncertainty to capture multiple possible partner states…
- arXiv cs.AIagentsGuideEvolve: Self-Evolving Agent Framework with Expert Guidance and 3Ts Mechanisms
arXiv:2610.30017v1 Announce Type: new Abstract: This study introduces GuideEvolve, a self-evolving agent framework incorporating expert guidance and three autonomous regulatory mechanisms, collectively termed the 3Ts: Th…
- arXiv cs.AIagentsRobust Soft Skill Adaptation via Behavioral Localization in Tool-Using Agents
arXiv:2610.30041v1 Announce Type: new Abstract: Text skills can extend the capabilities of tool-using agents, but long skill descriptions increase computational costs. Soft prompts provide a compact alternative, yet lear…
- arXiv cs.AIagentsHGM-Dual: Lineage-Aware Guided Agent Harness Optimization for Long-Horizon Planning
arXiv:2610.30042v1 Announce Type: new Abstract: Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Lea…
- arXiv cs.AIagentsCharts as Epistemic Actions for Experience-Driven Agentic Data Analysis
arXiv:2610.30072v1 Announce Type: new Abstract: Data agents built on ReAct-style loops now execute complex analytical workflows over structured data, yet their intermediate reasoning still runs almost entirely through te…
- arXiv cs.AIagentsCompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet Needs
arXiv:2610.28658v1 Announce Type: cross Abstract: How much can we trust an agent to find the paper we need? As researchers, we search the literature from what we have read toward what we have not. We thus describe what w…
- arXiv cs.AIagentsWho Verifies the Builder? Toward Independent Assurance for Agent-Produced Software
arXiv:2610.28667v1 Announce Type: cross Abstract: Coding agents can now implement a specification, write and run tests, repair failures, and declare the result ready for release. When the same agentic system produces bot…
- arXiv cs.AIagentsVerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents
arXiv:2610.28679v1 Announce Type: cross Abstract: Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruc…
- arXiv cs.AIagentsReinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey
arXiv:2610.28699v1 Announce Type: cross Abstract: Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs)…
- arXiv cs.AIagentsSecond Thoughts: Exploring and Planning through Comparative Imagination in World Models
arXiv:2610.28779v1 Announce Type: cross Abstract: World models let agents compare imagined outcomes before acting, but an agent must still decide which alternatives to explore and when a proposed plan should replace its…
- arXiv cs.AIagentsWhere Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
arXiv:2610.28834v1 Announce Type: cross Abstract: Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feed…
- arXiv cs.AIagentsAgent AI Zarz\k{a}dzaj\k{a}cy Sieci\k{a} Open RAN Zorientowana na U\.zytkownika
arXiv:2610.28860v1 Announce Type: cross Abstract: Jednym z najwa\.zniejszych wyzwa\'n zwi\k{a}zanych z implementacj\k{a} sieci Open RAN o architekturze zorientowanej na u\.zytkownika jest odpowiednie formowanie tzw. klas…
- arXiv cs.AIagentsJaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds
arXiv:2610.28907v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) offers a principled way of populating simulated economies with many heterogeneous decision makers. Its adoption, pioneered in fi…
- arXiv cs.AIagentsBlack-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
arXiv:2610.28966v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks. Prior black-box red-teaming attacks mainly focus on…
- arXiv cs.AIagentsVeriEvolve: Evaluator-First Evolution for Tool-Using Agents
arXiv:2610.29005v1 Announce Type: cross Abstract: A central obstacle to self-improving agents is the absence of a reliable fitness signal for realistic stateful tasks. We introduce \textsc{VeriEvolve}, an evaluator-first…
- arXiv cs.AIagentsAgentic Music Post-Production
arXiv:2610.29093v1 Announce Type: cross Abstract: We introduce MixAgent, an agentic pipeline for music post-production that follows the workflow of audio engineers to build interpretable and editable mixing plans guided…
- arXiv cs.AIagentsTrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence
arXiv:2610.29171v1 Announce Type: cross Abstract: We study how to improve training efficiency on Ascend NPUs. In the NPU training programs we study, framework-level compilation optimizations such as operator fusion are o…
- arXiv cs.AIagentsCorrelated Failures of AI Approval Monitors
arXiv:2610.29178v1 Announce Type: cross Abstract: Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined by aggregating scores…