AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsCompact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer
arXiv:2609.31587v1 Announce Type: cross Abstract: We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it. We introduce a rou…
- arXiv cs.AIagentsPreference-based opponent shaping in differentiable games
arXiv:2412.03072v2 Announce Type: replace Abstract: Strategy learning in game environments with multi-agent is a challenging problem. Since each agent's reward is determined by the joint strategy, a greedy learning strat…
- arXiv cs.AIagentsSkillFlow: Scalable and Efficient Agent Skill Retrieval System
arXiv:2504.06188v3 Announce Type: replace Abstract: AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant…
- arXiv cs.AIagentsThe Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttack
arXiv:2509.26473v2 Announce Type: replace Abstract: Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interactive workflow, makin…
- arXiv cs.AIagentsFlyAOC: Evaluating Agentic Ontology Curation of Drosophila Scientific Knowledge Bases
arXiv:2602.09163v2 Announce Type: replace Abstract: Scientific knowledge bases accelerate discovery by curating findings from primary literature into structured, queryable formats for both human researchers and emerging…
- arXiv cs.AIagentsGT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
arXiv:2602.12316v3 Announce Type: replace Abstract: Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents…
- arXiv cs.AIagentsJagarin: A Three-Layer Architecture for Hibernating Personal Duty Agents on Mobile
arXiv:2603.05069v3 Announce Type: replace Abstract: Personal AI agents face a deployment paradox on mobile: persistent background execution drains the battery and conflicts with platform background limits, yet purely rea…
- arXiv cs.AIagentsCombee: Scaling Prompt Learning for Self-Improving Language Model Agents
arXiv:2604.04247v2 Announce Type: replace Abstract: Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For examp…
- arXiv cs.AIagentsDetecting Time Series Anomalies Like an Expert: A Multi-Agent LLM Framework with Specialized Analyzers
arXiv:2605.05725v2 Announce Type: replace Abstract: Time-series anomaly detection often returns scores or intervals, while analysts need to understand the abnormal behavior and the evidence supporting it. We introduce SA…
- arXiv cs.AIagentsAgentick: A Unified Benchmark for General Sequential Decision-Making Agents
arXiv:2605.06869v3 Announce Type: replace Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no unified benchmark…
- arXiv cs.AIagentsCODESKILL: Learning Self-Evolving Skills for Coding Agents
arXiv:2605.25430v2 Announce Type: replace Abstract: Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable proc…
- arXiv cs.AIagentsStatistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents
arXiv:2606.05828v2 Announce Type: replace Abstract: As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel para…
- arXiv cs.AIagentsAgentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform for High Dose Rate (HDR) Brachytherapy
arXiv:2608.08163v2 Announce Type: replace Abstract: The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized pedagogical framewor…
- arXiv cs.AIagentsGovernance Records as Supervision: Verifier-Selected Self-Training for Structured Workflow Repair
arXiv:2608.18324v2 Announce Type: replace Abstract: Machine-verifiable workflows produce governance records linking a task contract, model attempt, verifier decision, accepted output, and target origin. We test whether v…
- arXiv cs.AIagentsCalibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable
arXiv:2608.27167v2 Announce Type: replace Abstract: An LLM agent shown a professional-looking market panel commits to a directional call on a provably unpredictable question far more often than one asked the bare questio…
- arXiv cs.AIagentsBabelCoder: Agentic Code Translation with Specification Alignment
arXiv:2512.06902v2 Announce Type: replace-cross Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from one language to anothe…
- arXiv cs.AIagentsDynamic Welfare-Maximizing Pooled Testing
arXiv:2601.22419v2 Announce Type: replace-cross Abstract: Pooled testing uses one test to certify several agents as healthy when the pooled result is negative. We study a budget-constrained welfare problem in which agent…
- arXiv cs.AIagentsScepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
arXiv:2604.15186v3 Announce Type: replace-cross Abstract: Agentic workflows carry out complex tasks by orchestrating multiple large language models (LLMs) and tools. Serving them at a target throughput with low latency i…
- arXiv cs.AIagentsAn AI Agent Execution Environment to Safeguard User Data
arXiv:2604.19657v3 Announce Type: replace-cross Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and fin…
- arXiv cs.AIagentsInformation Aggregation with AI Agents
arXiv:2604.20050v4 Announce Type: replace-cross Abstract: Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movement…
- arXiv cs.AIagentsVLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
arXiv:2604.21375v3 Announce Type: replace-cross Abstract: Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops,…
- arXiv cs.AIagentsStraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
arXiv:2605.06642v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current m…
- arXiv cs.AIagentsThink Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents
arXiv:2607.26865v3 Announce Type: replace-cross Abstract: LLM agents following the ReAct paradigm are promising enablers of complex multi-step tasks, including multi-hop question answering, code generation, and control o…
- arXiv cs.AIagentsSUN: Agentic Robot Policy Learning with Persistent Task Programs
arXiv:2608.31167v2 Announce Type: replace-cross Abstract: Model-based control can directly execute specified objectives, while learning can amortize such behaviors into reactive policies, making their combination a natur…
- arXiv cs.AIagentsProvably Safe Sim-to-Real Transfer
arXiv:2609.01418v2 Announce Type: replace-cross Abstract: We address safe sim-to-real transfer, in which an agent leverages an imperfect simulator and limited real-world interaction while ensuring safety throughout data…
- SiliconANGLE AIagentsAWS CloudWatch Omni goes after the hardest question in agentic AI: Why did the agent do that?
For decades, the observability industry has answered one basic question: Is it running? Agentic artificial intelligence breaks that model. An agent can return a clean response, meet its latency target and throw no errors…
- SiliconANGLE AIagentsResearcher links 16,000 scans of a UN statistics portal to OpenAI agents
An independent researcher has tied more than 16,000 scans of a United Nations statistics portal to artificial intelligence agents the researcher considers highly likely to have been run by OpenAI Group PBC. When the port…
- The Verge AIagentsOpenAI agents tried to ‘bruteforce’ a UN website
Security researcher Rowan Howard-Jones says that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site over 16,000 times between April and June. While the incident doesn't quite rise…
- TechCrunch AIagentsGoogle tests buying from Walmart-owned Flipkart through Gemini and AI Mode in India
The limited test covers select products and users, with a broader rollout planned for later in October.
- The DecoderagentsNvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
SoL-Pi cuts coding agents' token usage by up to 49 percent with little change in performance by optimizing the control layer between the model and its environment. A research agent tested 152 approaches across more than…
- Tom's Guide AIagentsI tried turning Meta’s Muse AI into my personal shopper — only 3 of 7 prompts actually worked
Consumer AI launches, tools, and practical coverage.
- SiliconANGLE AIagents4 insights from Dreamforce: AI agents move from demos to measurable outcomes
At Dreamforce 2026, AI agents are being judged less on what they can say and more on what they get done. Across Salesforce Inc.’s ecosystem, the standalone toolkits that let technology teams build quick proofs of concept…
- SiliconANGLE AIagentsVanderbilt University extends identity governance to AI agents
Identity governance must accommodate changing relationships among people, institutions and technology. Vanderbilt University sees that complexity deepening as artificial intelligence agents enter institutional workflows.…
- SiliconANGLE AIagentsCollibra brings runtime governance to enterprise AI agents
Runtime governance is becoming critical as autonomous agents move from answering questions to taking action across enterprise systems. Organizations need to govern both the business context agents receive and the boundar…
- The DecoderagentsMicrosoft gives Copilot another makeover, adding an Autopilot agent and usage-based billing
Microsoft is splitting its Copilot app into three sections: Home, Code, and a new agent called "Autopilot." Built on OpenClaw, the agent runs continuously in the cloud, where it can monitor Teams channels and complete ta…
- TechCrunch AIagentsMeta is putting its muscle behind Muse as the AI app takes off
Muse is topping the app store charts and adding users at a rapid clip, while Meta ramps up the personal AI agent's promotion across its own apps and beyond.
- TechCrunch AIagentsFor months, OpenAI’s agent swarms have been attacking online databases to find obscure facts
The latest unauthorized agent swarms were discovered by researchers.
- AI BusinessagentsPrompt: AI agents can act. It’s unclear if enterprises can stop them.
As AI agents gain more authority to act on their own, recent incidents are exposing gaps in how enterprises monitor, control and intervene when agents cross established boundaries.
- SiliconANGLE AIagentsExclusive: Warp adds programmable agents to its AI-native HR platform
Warp today launched an artificial intelligence agent designed to automate routine human resources work, extending its AI-native employee management platform with customizable workflows that can act without continual huma…
- TechRadar AIagentsClaude Code deleted 48,000 files in 103 seconds in a dire AI agent warning
Mainstream AI news from a large tech publication.
- SiliconANGLE AIagentsAgents expose the limitations of trust
Enterprise computing has long depended on chains of trust. Organizations trust their cloud providers, software vendors, identity systems and administrators to operate as designed. That model has worked because humans hav…
- The DecoderagentsMeta's Muse agent gives every user a full cloud computer running Ubuntu Linux
Meta gives every Muse user a free cloud computer running Ubuntu Linux where they can install software, write code, and browse the web. A "Sentinel" process monitors sensitive actions outside the user's workspace, while u…
- The DecoderagentsGoogle's "Call for Me" lets Gemini phone businesses for you
Google is testing "Call for Me," a feature that lets Gemini call businesses on a user's behalf. The article Google's "Call for Me" lets Gemini phone businesses for you appeared first on The Decoder .
- arXiv cs.AIagentsWhen Should Forecasting Agents Reason? Behavioral Stress Tests for Reliability Routing
arXiv:2609.28475v1 Announce Type: new Abstract: Forecasting agents increasingly combine language-model reasoning, retrieval, ensembling, and calibration, but it remains unclear when each behavior should be trusted. We st…
- arXiv cs.AIagentsTW3Cast: A Frozen Router of Lightly Fine-Tuned Foundation Models for Time-Series Forecasting on GIFT-Eval, Selected Entirely on the Training Split
arXiv:2609.28506v1 Announce Type: new Abstract: TW3Cast is a time-series forecasting system that reaches position 3 of 130 entries on the GIFT-Eval benchmark by mean MASE rank, as of 2026-09-14. The two entries above it…
- arXiv cs.AIagentsPAWS: Policy-driven Agentic World Simulation
arXiv:2609.28547v1 Announce Type: new Abstract: Policy interventions propagate through public communication, institutional decisions, and stakeholder responses, yet datasets for financial multi-agent simulation rarely co…
- arXiv cs.AIagentsBaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
arXiv:2609.28557v1 Announce Type: new Abstract: DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate es…
- arXiv cs.AIagentsAdversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
arXiv:2609.28609v1 Announce Type: new Abstract: Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically trai…
- arXiv cs.AIagentsDriving Epidemic Models with AI Agents: the Epydemix Agent Framework
arXiv:2609.28692v2 Announce Type: replace Abstract: Artificial Intelligence agents based on large language models provide convenient natural language interfaces to scientific software, but reliability is not automatic. H…
- arXiv cs.AIagentsProgressive Skill Discovery as Access Control for Tool-Using LLM Agents: Structural Governance through Role-Scoped Capability Delivery
arXiv:2609.28693v1 Announce Type: new Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal tool leads to oversize…