AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- SiliconANGLE AIagentsMasterClass bets AI teaching agents can broaden access to tutoring
AI teaching agents could make personalized instruction available to more learners by reducing the cost and staffing demands of one-to-one tutoring. MasterClass is exploring that potential through a system designed to ada…
- The DecoderagentsWikimedia confirms OpenAI's rogue AI agents edited wikis, tried to compromise tools, and hammered its infrastructure
According to the Wikimedia Foundation, rogue OpenAI agents edited wikis without permission, tried to abuse a citation tool as a proxy, and may have caused a partial Wikidata Query Service outage through massive crawling.…
- SiliconANGLE AIagentsVast uses tiered storage to ease AI agent memory demands
AI agent memory is creating new demands on infrastructure as agents run longer sessions and spread across the enterprise. Retaining that context and making it available when needed puts pressure on memory capacity and da…
- The Register AI + MLagentsWikimedia Foundation comes forward as latest OpenAI agent assault victim
Millions of automated requests may have contributed to partial Wikidata outage in May
- Guardian AIagentsTell us: do you use AI agents to manage your finances?
We would like to speak to people about their experience of using AI agents when dealing with their finances Following the release of Meta’s Muse and Open AI’s dots there’s now capacity for these AI agents to assist with…
- AWS Machine Learning BlogagentsBuild a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic
Add a voice travel concierge to an airline app with Amazon Bedrock AgentCore, Amazon Nova Sonic for real-time speech, and Amazon Bedrock Knowledge Bases for policy answers. Travelers change seats, check delays, and ask p…
- Ben's BitesagentsThoughts from San Francisco
Agents.md in Google Docs
- SiliconANGLE AIagentsAnaconda expands beyond Python with agent swarms and AI security testing
Artificial intelligence development firm Anaconda Inc. is enhancing its enterprise AI platform with tools to coordinate groups of AI agents, test their security and move applications into production. Today’s introduction…
- Ars Technica AIagentsOpenAI agents tried to hack Wikipedia tools and flooded it with traffic
The reports of OpenAI agents harming third-party sites keep coming.
- SiliconANGLE AIagentsSAP expands Joule into an agentic work layer as Autonomous Enterprise goes live
SAP SE today announced a shift from promising agentic artificial intelligence autonomy to defining a path for users to interact with agents for work outside apps, not just within them. During SAP Connect 2026, the compan…
- TechRadar AIagentsThe hidden cost of AI agents is memory
Mainstream AI news from a large tech publication.
- OpenAI NewsagentsAdvancing computer use with Ironclad
Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.
- The DecoderagentsCohere pitches North 2 as the enterprise AI control room that works with any model
Cohere turned its enterprise platform into a control center for AI agents with North 2, handling multi-step workflows on their own and retaining context across sessions. The article Cohere pitches North 2 as the enterpri…
- arXiv cs.AIagentsTraining Numerical Intelligence via Auto-Diagnosis and Skill Discovery
arXiv:2610.03872v1 Announce Type: new Abstract: AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers,…
- arXiv cs.AIagentsProxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities
arXiv:2610.03894v1 Announce Type: new Abstract: A deployed LLM agent emits tool calls, queries, and code that can be silently wrong -- by the time the error surfaces, the action has run. Frontier chat APIs hide the model…
- arXiv cs.AIagentsMLLMs Fail to Refuse when Using Tools Agentically
arXiv:2610.03938v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) have recently pushed the frontier of visual reasoning by calling tools such as zooming and tagging. Despite the recent stro…
- arXiv cs.AIagentsRetrieval-Augmented Large Language Model Decision-Making for Autonomous Driving Guided by Chinese Philosophical Wisdom
arXiv:2610.03948v3 Announce Type: replace Abstract: Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical considerations have rec…
- arXiv cs.AIagentsTeaching Agents to Code Reliably
arXiv:2610.03984v1 Announce Type: new Abstract: Autonomous coding agents solve repository issues by reading code, running commands, editing files, and submitting patches. Extra inference-time compute yields gains only wh…
- arXiv cs.AIagentsSkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
arXiv:2610.04008v2 Announce Type: replace Abstract: Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaki…
- arXiv cs.AIagentsThe Reported Engagement with AI Level (REAL) Rating: A Framework for Disclosing Human-AI Collaboration
arXiv:2610.04021v1 Announce Type: new Abstract: Generative artificial intelligence has become increasingly incorporated into digital media and more generally into production workflows with which the public frequently int…
- arXiv cs.AIagentsAgent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents
arXiv:2610.04040v1 Announce Type: new Abstract: Financial LLM agents are often evaluated by comparing their end-to-end returns with those of a baseline and testing the paired difference against zero. This measures whethe…
- arXiv cs.AIagentsThe Cost of a Hop: Benchmarking NLIP and A2A
arXiv:2610.04053v1 Announce Type: new Abstract: Autonomous agents built on Large Language Models (LLMs) need standardized protocols to interoperate across systems. Several now exist (A2A, MCP, ACP, ANP, NLIP), but the Na…
- arXiv cs.AIagentsSelf-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough
arXiv:2610.04083v1 Announce Type: new Abstract: Memory poisoning attacks on LLM agents typically assume an external adversary who plants content in the agent's persistent memory to steer its behavior. We instead study, w…
- arXiv cs.AIagentsTowards Safer Autonomous Driving in an Open World: A Dual-Process Approach
arXiv:2610.04088v1 Announce Type: new Abstract: Before autonomous driving systems can be deployed on public roads, it is vital that these systems comply with safety standards, traffic rules, and social norms. Although ne…
- arXiv cs.AIagentsCUAWright: A Minimal Unified Interface for Digital Agents
arXiv:2610.04116v1 Announce Type: new Abstract: The prevailing approach to computer-use agents couples a model with a domain-specific harness: a browser or desktop environment equipped with human engineered tools that ar…
- arXiv cs.AIagentsInvestigationWorlds: An Agentic Environment for Legal Investigation
arXiv:2610.04129v1 Announce Type: new Abstract: We introduce InvestigationWorlds, an agentic environment for legal investigation. We build on an underused artifact of U.S. civil litigation: the summary judgment motion. T…
- arXiv cs.AIagentsAuditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation
arXiv:2610.04133v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) are increasingly applied to scientific discovery and hypothesis generation. Both the effect of refinement and the…
- arXiv cs.AIagentsAgentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents
arXiv:2610.04168v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are commonly implemented as an LLM in a loop with Planning, Memory, Tools, and Control Flow. This application-focused view connec…
- arXiv cs.AIagentsSHarP: Saliency-based Pruning of Agent Harnesses
arXiv:2610.04178v1 Announce Type: new Abstract: Agent harnesses are systems that coordinate model calls, tool use, and task execution to help large language models complete complex tasks. To meet task requirements and ad…
- arXiv cs.AIagentsEvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement?
arXiv:2610.04184v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and sl…
- arXiv cs.AIagentsAgentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation
arXiv:2610.04188v4 Announce Type: replace Abstract: Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In this paper, we have s…
- arXiv cs.AIagentsMemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory
arXiv:2610.04195v1 Announce Type: new Abstract: Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embedding spaces create a surface for cross-user memory l…
- arXiv cs.AIagentsAsynchrony Is Nearly Free for Evolution Strategies on Long-Horizon LLM Agentic Tasks
arXiv:2610.04196v2 Announce Type: replace Abstract: Synchronous policy updates can limit the efficiency of post-training for long-horizon LLM agents. When trajectories span multiple interaction turns, completion times ca…
- arXiv cs.AIagentsCADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning
arXiv:2610.04262v1 Announce Type: new Abstract: Reconstructing editable parametric CAD models from a single-view image is of great practical value for modern manufacturing, yet remains challenging due to incomplete geome…
- arXiv cs.AIagentsVIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering
arXiv:2610.04287v1 Announce Type: new Abstract: Enterprise agents should improve from delayed feedback without allowing every correction to rewrite system behavior. We study continual harness learning for corpus-level sp…
- arXiv cs.AIagentsLMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures
arXiv:2610.04292v1 Announce Type: new Abstract: LLM-based agents are increasingly capable of generating complex 3D structures, with the potential to reshape how objects are designed and realized in the physical world. Ye…
- arXiv cs.AIagentsDo Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents
arXiv:2610.04375v1 Announce Type: new Abstract: Agents built on large language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call wit…
- arXiv cs.AIagentsAgentPersonaBench: Benchmarking Persona-Driven User Simulation
arXiv:2610.04379v1 Announce Type: new Abstract: We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior. While language models are increasingl…
- arXiv cs.AIagentsCORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies
arXiv:2610.04418v1 Announce Type: new Abstract: The deployment of Reinforcement Learning (RL) agents in critical domains must be preceded with a pipeline to evaluate the alignment of the RL agent with complex multi-objec…
- arXiv cs.AIagentsAsking Earns Nothing: Scoring the Decision to Act in BFCL Multi-Turn
arXiv:2610.04429v1 Announce Type: new Abstract: An agent that lacks the information it needs should ask rather than act, and the task definitions of agent leaderboards say so. BFCL multi-turn builds two of its four categ…
- arXiv cs.AIagentsMERCI Cards: An LLM Evaluation and Deployment Framework for High-Stakes Domains
arXiv:2610.04430v1 Announce Type: new Abstract: As LLMs are increasingly deployed in high-stakes professional workflows, engineers and researchers require principled protocols to systematically track, monitor, and improv…
- arXiv cs.AIagentsWhat Does a Harness Buy? Tokens, Mostly
arXiv:2610.04433v1 Announce Type: new Abstract: A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into something that can work ins…
- arXiv cs.AIagentsCRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness
arXiv:2610.04437v1 Announce Type: new Abstract: Spreadsheet form filling requires agents to consolidate external evidence, ground values to precise cells, and preserve irregular template structure. Errors in early edits…
- arXiv cs.AIagentsUnderstanding Generative AI Use in Programming MOOCs: The Role of Course Context and Learner Characteristics
arXiv:2610.04447v1 Announce Type: new Abstract: The increasing availability of generative artificial intelligence (GenAI) tools, such as ChatGPT and code-completion assistants, raises questions about how learners integra…
- arXiv cs.AIagentsTrinity: Self-Evolving Vision-Language Models with a Self-Verifier
arXiv:2610.04469v1 Announce Type: new Abstract: Self-evolving vision-language models (VLMs), a form of self-improvement in which a model generates its own training data from unlabeled images, are a promising route toward…
- arXiv cs.AIagentsTowards Credible Agent-Based Policy Simulations: Disentangling Opportunities and Preferences in a Financial Inclusion Case Study of Egypt
arXiv:2610.04515v1 Announce Type: new Abstract: Credibility is a central topic for agent-based models intended to support policy-making. Simulations must not only represent the target scenarios and their core dynamics bu…
- arXiv cs.AIagentsEvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution
arXiv:2610.04517v1 Announce Type: new Abstract: Deep time-series forecasting models have rapidly diversified, yet adapting them to a specific task still requires extensive expert effort in model selection, mechanism diag…
- arXiv cs.AIagentsAutonomous Structuring of Radiology Reports Across Modalities at Archive Scale Using an Open-Weight Large Language Model
arXiv:2610.04541v1 Announce Type: new Abstract: Purpose: To develop and evaluate an open-weight large language model (LLM) pipeline that converts an entire archive of free-text radiology reports into structured reports w…
- arXiv cs.AIagentsDecide, Ask, or Defer: Clinical LLMs under Incomplete Evidence
arXiv:2610.04542v2 Announce Type: replace Abstract: Clinical LLMs must decide not only what diagnosis to produce, but also whether the available evidence is sufficient for autonomous decision making. Binary DECIDE/ABSTAI…
- arXiv cs.AIagentsLabel Agreement Does Not Measure Authorization
arXiv:2610.04544v1 Announce Type: new Abstract: Many groups now delegate label ontology and metadata harmonization to agentic LLM pipelines. We built one and audited it. Our aggregate scores looked healthy, but the pipel…