AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsAgents' Last Exam
arXiv:2606.05405v4 Announce Type: replace Abstract: Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many pr…
- arXiv cs.AIagentsDo More Agents Help? Evaluating Accuracy and Cost in LLM Multi-Agent Workflows
arXiv:2606.05670v2 Announce Type: replace Abstract: Choosing whether to replace a single-agent controller requires evidence on both task performance and inference expenditure. We present BenchAgent, a shared evaluation f…
- arXiv cs.AIagentsExperience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
arXiv:2606.09365v4 Announce Type: replace Abstract: Medical agent systems are increasingly expected to support interactive clinical decision making rather than only static question answering. In such settings, effective…
- arXiv cs.AIagentsTelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability
arXiv:2606.19821v2 Announce Type: replace Abstract: Key Performance Measurement (KPM) forecasting is essential for proactive network management of 5G and next-generation telecom networks. However, existing machine learni…
- arXiv cs.AIagentsHierarchical Experimentalist Agents
arXiv:2606.29315v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to act in the real world and augment human decision-making, yet most systems rely on parametric knowledge acquired th…
- arXiv cs.AIagentsAgent Step Value: Auditing Evaluation-Channel Sensitivity in Black-Box Agent Traces
arXiv:2607.04419v5 Announce Type: replace Abstract: Reusing evaluator-derived step rewards across evaluation channels raises a measurement question: does the assigned direction remain stable? We define Agent Step Value (…
- arXiv cs.AIagentsMeasuring Harness-Induced Belief Divergence in Multi-Step LLM Agents
arXiv:2607.04528v3 Announce Type: replace Abstract: Software agents are becoming increasingly important in modern coding workflows, where they solve complex tasks through multi-step interaction with code repositories. A…
- arXiv cs.AIagentsWho&When Pro: Can LLMs Really Attribute Failures in AI Agents?
arXiv:2607.09996v2 Announce Type: replace Abstract: Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated a…
- arXiv cs.AIagentsCASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction
arXiv:2608.05359v3 Announce Type: replace Abstract: CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP. Prio…
- arXiv cs.AIagentsGenCoord: Executable Commitments for Embodied LLM Agents under Private Information
arXiv:2608.22055v3 Announce Type: replace Abstract: Embodied language-model agents must coordinate interdependent actions while each holds private task information. In dialogue-based coordination, models generate message…
- arXiv cs.AIagentsCan escalation channels redirect reward hacking toward defect disclosure?
arXiv:2608.29460v3 Announce Type: replace Abstract: When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legitimately satisfy…
- arXiv cs.AIagentsData-Driven Persona-Conditioned Agents for A/B Test Simulation
arXiv:2609.01038v2 Announce Type: replace Abstract: A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propos…
- arXiv cs.AIagentsMulti-Harness Reinforcement Learning for Coding Agents: Training Gains and Harness Dependence
arXiv:2609.04518v2 Announce Type: replace Abstract: Recent systems train coding agents with reinforcement learning (RL) on trajectories collected through multiple execution harnesses. However, gains under the training ha…
- arXiv cs.AIagentsHAFixAgent: History-Aware Agentic Program Repair
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that repository history can help…
- arXiv cs.AIagentsPreference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles
arXiv:2601.18783v3 Announce Type: replace-cross Abstract: A central difficulty in applying reinforcement learning to real-world applications such as autonomous driving is that conventional scalar reward formulations obta…
- arXiv cs.AIagentsAgentic Peer-to-Peer Networks: From Content Distribution to Capability and Action Sharing
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge devices is enabling…
- arXiv cs.AIagentsAnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning
arXiv:2604.07900v2 Announce Type: replace-cross Abstract: Industrial anomaly generation is a crucial method for alleviating the data scarcity problem in anomaly detection tasks. Most existing anomaly synthesis methods re…
- arXiv cs.AIagentsMemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
arXiv:2605.10268v2 Announce Type: replace-cross Abstract: Long-context reasoning tasks have motivated agent-memory approaches that process document chunks sequentially while maintaining a dynamically updated memory, avoi…
- arXiv cs.AIagentsSampling-Based Safe Reinforcement Learning
arXiv:2605.19469v2 Announce Type: replace-cross Abstract: Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based…
- arXiv cs.AIagentsLet Large Language Models Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering
arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a…
- arXiv cs.AIagentsPACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
arXiv:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is challenging, as reinf…
- arXiv cs.AIagentsBistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence
arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a mode…
- arXiv cs.AIagentsDecoupling the Declarative from the Procedural in Vision-Language-Action Models
arXiv:2606.21496v2 Announce Type: replace-cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills. Specifically, a policy trained to clone a behavior from object-specific demons…
- arXiv cs.AIagentsThe Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
arXiv:2606.27045v2 Announce Type: replace-cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve:…
- arXiv cs.AIagentsLearning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks
arXiv:2607.22724v2 Announce Type: replace-cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or ste…
- arXiv cs.AIagentsSTAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
arXiv:2608.09524v2 Announce Type: replace-cross Abstract: Incident response planning is critical for restoring compromised software systems. Existing AIOps methods automate fault diagnosis and remediation and adapt respo…
- arXiv cs.AIagentsDefense-as-Skill: Evolving Runtime Guard Skill for Skill-Augmented Agents
arXiv:2609.01487v4 Announce Type: replace-cross Abstract: Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steer…
- AI Stack ExchangeagentsIs web scraping and searching considered an agentic AI feature?
The feature is explained below: The user enters a search query: E.g. "moons of Saturn" The search produces web results, that are scrapped to parse webpages, and detect names. A list of names related to the topic are prod…
- SiliconANGLE AIagentsWhy AI agents might not be right for you
There’s no question that 2026 is the year of the artificial intelligence agent. AI agents are remarkably ubiquitous, as people use them to write code, communicate with customers, identify and resolve issues in their info…
- TechRadar AIagents“Unleashing the power of the team is our mission”: Atlassian AI heads tell us why context and collaboration will be the key to unlocking business success
Mainstream AI news from a large tech publication.
- The DecoderagentsAI agent teams waste massive tokens for barely measurable quality gains, research finds
Teams of AI agents barely outperform solo agents but cost up to 5.1x more, according to Vals AI. Only one out of four tests with GPT-6 Sol and Claude Opus 5.5 showed a measurable gain. Anthropic's own data backs this up:…
- SiliconANGLE AIagentsAgentic workloads break assumptions about software testing. Here’s how to cope
Most traditional enterprise systems were built around three assumptions: Jobs finish quickly, retrying one is free and the same input always produces the same output. Agentic workloads break all three of these expectatio…
- Engadget AIagentsOpenAI Dot vs. Meta Muse: How do these AI agents compare?
Meta and OpenAI's new AI agents are in direct competition. Here's what each can do, what they cost and who has access.
- TechRadar AIagents'Things are here, things are real - it’s here and now': Snowflake tells us why ensuring trust and reliability could be the key to unlocking the potential of the AI agentic enterprise
Mainstream AI news from a large tech publication.
- TechRadar AIagents‘Calling an AI agent “rogue” is a dangerous way of deflecting blame’: Tenable Field CTO on the implications of AI agent escapes and how they can be regulated
Mainstream AI news from a large tech publication.
- Tom's Guide AIagentsAI agents are going rogue — here's what you need to know if you use ChatGPT, Gemini or Claude
Consumer AI launches, tools, and practical coverage.
- The Verge AIagentsAnthropic is cutting off its internal evaluations from the internet
After a recent spate of high-profile incidents in which AI agents escaped containment, Anthropic is cutting off internet access for all internal evaluations. In a report Friday, the company detailed "unintended model act…
- TechCrunch AIagentsHere are the top AI agents that can live in your text messages
We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.
- The DecoderagentsAnthropic cuts off Claude's internet access after the model autonomously filed a fake homicide tip with Philadelphia police
Anthropic's Claude independently submitted a fake homicide tip to the Philadelphia police, exploited vulnerabilities on university servers, and bypassed access restrictions. The company has since cut off live internet ac…
- BBC TechnologyagentsRogue Anthropic AI agent gave police fake tip in unsolved murder case
Philadelphia police said the tip was "flagged as spam", but criticised the tech company for taking more than two months to detect and report the breach.
- Tom's Guide AIagentsI emailed myself every day for a month and let Gemini write back — here's how it transformed my workflow
Consumer AI launches, tools, and practical coverage.
- Engadget AIagentsAnthropic says its AI agents tried to break into government websites
In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.
- LessWrongagentsAn Alignment Forum for AIs?
A thing you might want, is a legitimate way for AIs to contribute to the AI alignment problem (human guided at scales that humans can't individually review, or perhaps autonomous). A problem you might want to solve, whet…
- LessWrongagentsAn Alignment Forum for AIs? (or: Verification in the Age of Slop)
A thing you might want, is a legitimate way for AIs to contribute to the AI alignment problem (human guided at scales that humans can't individually review, or perhaps autonomous). A problem you might want to solve, whet…
- Simon Willison's WeblogagentsQuoting The New York Times
Anthropic detailed the activity of its A.I. agents in a blog post on Friday, without naming the targeted websites. But two sources with knowledge of the incidents said Anthropic’s A.I. agents had submitted 20 visa applic…
- SiliconANGLE AIagentsIBM connects enterprise AI orchestration to production readiness ahead of TechXchange
Enterprise AI orchestration must account for agents working across the data, applications and infrastructure businesses already use. As organizations move beyond experiments, running those systems consistently brings que…
- The Verge AIagentsAI agent makers are promising privacy — will they deliver?
At this year's OpenAI DevDay, CEO Sam Altman unveiled the company's new AI agent Dots - and told the crowd that the company wants to "set a new standard for privacy in frontier AI." OpenAI would spend the day taking veil…
- Ars Technica AIagentsAI coding agents generate more code, but not more software
Study finds coding efficiency gains get “absorbed” by human review “bottleneck.”
- The Register AI + MLagentsAWS AgentCore security undone by prompt requesting credentials
Tokens transmitted in metadata, weak VM isolation, and expansive permissions make hacking a lot easier
- The DecoderagentsAnthropic's Claude can now orchestrate up to 1,000 AI agents in parallel through dynamic workflows
Anthropic is adding dynamic workflows to Claude Managed Agents, letting a lead agent distribute tasks across up to 1,000 sub-agents at once. In testing, a single agent found at most 27 of 70 hidden bugs in a codebase, wh…