AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsCIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents
arXiv:2607.14386v2 Announce Type: replace Abstract: Enterprise data science and analytics spans closed-ended information extraction with verifiable answers and open-ended insight discovery. Agents are evaluated on one or…
- arXiv cs.AIagentsArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management
arXiv:2607.20764v2 Announce Type: replace Abstract: We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across…
- arXiv cs.AIagentsSpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
arXiv:2607.27703v3 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions bas…
- arXiv cs.AIagentsMeasurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation
arXiv:2608.00794v5 Announce Type: replace Abstract: Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims. No formal framework…
- arXiv cs.AIagentsGENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
arXiv:2608.09921v3 Announce Type: replace Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis,…
- arXiv cs.AIagentsRecovering Wasted Compute in Autoresearch Agents
arXiv:2608.10424v2 Announce Type: replace Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have inspired large ind…
- arXiv cs.AIagentsTrace Integrity for LLM Data Agents: Auditing Structured-Data Computation Beyond Answer Accuracy in Real-World Systems
arXiv:2608.26036v2 Announce Type: replace Abstract: Large language model (LLM) data agents answer structured-data questions by generating SQL, invoking tools, executing queries, and summarizing results. In operational se…
- arXiv cs.AIagentsFinLifeBench: Exhaustive Life-Event History and Financial-State Reconstruction from Longitudinal Banking Dialogue
arXiv:2609.01198v3 Announce Type: replace Abstract: Repeated banking interactions require assistants to maintain complete, current, and traceable customer records as life changes emerge incidentally in routine requests.…
- arXiv cs.AIagentsEvaluating LLM-based Agents for Multi-Turn Conversations: A Survey
arXiv:2503.22458v3 Announce Type: replace-cross Abstract: This survey examines evaluation methods for large language model (LLM)-based agents in multi-turn conversational settings. Using a PRISMA-inspired framework, we s…
- arXiv cs.AIagentsDeALOG: Decentralized Multi-Agents Log-Mediated Reasoning Framework
arXiv:2602.00996v3 Announce Type: replace-cross Abstract: Complex question answering across text, tables and images requires integrating diverse information sources. A framework supporting specialized processing with coo…
- arXiv cs.AIagentsMulti-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks
arXiv:2602.07215v2 Announce Type: replace-cross Abstract: Generative AI (GenAI) has transformed applications in natural language processing and content creation, yet centralized inference remains hindered by high latency…
- arXiv cs.AIagentsEpiFlow: Bridging Safety and Performance in Offline Reinforcement Learning via Epigraph-Guided Flow Matching
arXiv:2602.08054v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) offers a promising framework for deploying autonomous systems in safety-critical settings without the risks of online explorat…
- arXiv cs.AIagentsRoboGene: Diversity-Driven Agentic Task Generation Framework for VLA Pre-training
arXiv:2602.16444v3 Announce Type: replace-cross Abstract: The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike large-scale web vision-language da…
- arXiv cs.AIagentsAutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models
arXiv:2603.28963v3 Announce Type: replace-cross Abstract: Simulation with realistic traffic agents is essential for validating autonomous driving systems. Existing data-driven simulators learn agent behavior from higher-…
- arXiv cs.AIagentsSame Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
arXiv:2605.06908v2 Announce Type: replace-cross Abstract: Adaptive test-time compute for LLM agents aims to invoke extra computation only when it improves performance. Existing methods typically use confidence-, uncertai…
- arXiv cs.AIagentsWeb Agents Should Adopt the Compile-and-Execute Paradigm
arXiv:2605.14290v2 Announce Type: replace-cross Abstract: ReAct has become the default architecture across LLM agents, and many existing web agents follow this paradigm. We argue that it is the wrong default for web agen…
- arXiv cs.AIagentsEnhancing Software Engineering Through Closed-Loop Memory Optimization
arXiv:2606.05646v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues. Howev…
- arXiv cs.AIagentsLeadership as Coordination Control: Behavioral Signatures and the Recovery-Advantage Boundary in Multi-Agent LLM Teams
arXiv:2606.19111v2 Announce Type: replace-cross Abstract: Team science holds that leadership is contingent: it helps only under specific conditions. We ask the same question of multi-agent LLM teams: under what measurabl…
- arXiv cs.AIagentsMatching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents
arXiv:2606.21140v3 Announce Type: replace-cross Abstract: Rapid advances in large language models have improved the task-solving capabilities of command-line-interface (CLI)-based agents, whose CLIs determine how models…
- arXiv cs.AIagentsSafeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants
arXiv:2607.13039v3 Announce Type: replace-cross Abstract: Refusal rates conflate upstream provider behavior with downstream safeguards and do not reveal what information remains in a delivered answer. Safeguard-condition…
- arXiv cs.AIagentsCompaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes
arXiv:2607.13071v2 Announce Type: replace-cross Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper documents a failur…
- arXiv cs.AIagentsWhat the Abstention Option Measures: Refusal Loss, Sampling Churn, and Option Capture in Distilled Small Language Models
arXiv:2607.28639v3 Announce Type: replace-cross Abstract: Small instruction-tuned language models reach phones, cars, and offline assistants through knowledge distillation, and whether a distilled model is fair enough to…
- arXiv cs.AIagentsEntailLLM: Verifying Agent-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming
arXiv:2608.01763v2 Announce Type: replace-cross Abstract: Large language model agents are increasingly used to analyze potential software vulnerabilities, but their outputs can silently violate domain knowledge, limiting…
- arXiv cs.AIagentsBeyond Trial-and-Error: Agentic Optimization for Image-to-Video Adherence
arXiv:2608.12290v2 Announce Type: replace-cross Abstract: Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability pre…
- arXiv cs.AIagentsAgentLogs: A Dataset for Opening the Black Box of Cloud Agents on GitHub
arXiv:2608.29204v2 Announce Type: replace-cross Abstract: Coding agents now complete development tasks in real software projects and submit the results as pull requests. A pull request shows the outcome of an agent's exe…
- arXiv cs.AIagentsAgent Memory Is a Surface for Endogenous Authorization Laundering
arXiv:2609.01836v2 Announce Type: replace-cross Abstract: Long-running LLM agents rely on persistent memory to preserve not only task context but also the permissions and restrictions governing their actions. When memory…
- arXiv cs.AIagentsAgentic Societies Need a Social Harness
arXiv:2609.17527v2 Announce Type: replace-cross Abstract: An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries on behalf of different principals. We show experimentally tha…
- TechCrunch AIagentsHow OpenAI turned its coding tools into dots, an always-on personal assistant
Alexander Embiricos, the OpenAI executive responsible for dots, never wants to have a meeting with someone else's AI agent.
- SiliconANGLE AIagentsThree insights you may have missed from theCUBE’s coverage of Workiva’s Amplify event
Enterprise AI governance is moving into the data, workflows and controls that determine what automated systems can do. As agents take on consequential work in finance, audit, compliance and sustainability, organizations…
- TechRadar AIagentsAI agents need limits on financial access
Mainstream AI news from a large tech publication.
- AI Stack ExchangeagentsHow can I evaluate a clarification policy separately from the extra information supplied by its oracle?
I am working on the evaluation design for an offline reasoning-agent prototype. It currently exercises three scripted policies: answer directly, revise an answer without new external information, and optionally ask one c…
- SiliconANGLE AIagentsWhat to watch for as enterprises move from AI experimentation to autonomous operations
For the past three years, the enterprise artificial intelligence conversation has focused on what models can say. The next three years will be about what systems are allowed to do. That’s a harder problem that better mod…
- TechRadar AIagentsHow to create custom AI agents for your business in Wix Symphony
Mainstream AI news from a large tech publication.
- Latent SpaceagentsSupabase’s Plan for a Billion AI-Built Apps
AI agents are creating more software—and that changes what a backend needs to do. Supabase co-founders Paul Copplestone and Ant Wilson join swyx to discuss running long-lived workloads alongside the database, making sche…
- The Verge AIagentsThe RealReal won’t let AI agents hog designer clothing
The RealReal, a secondhand luxury fashion consignment retailer, said it's updating its bot defense system, effectively making it harder for AI agents to shop on its site. The change comes days after The Verge reported th…
- AWS Machine Learning BlogagentsGroundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock
Every time an agent takes a step, it re-reads its entire context before acting. Here is how prompt caching for OpenAI models on Amazon Bedrock lets your agent remember, cutting input cost and latency without resending th…
- AWS Machine Learning BlogagentsBuild agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK
Build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS CDK: an agent that routes across two knowledge bases, retrieves through the AgentCore Gateway, and returns grounded, cited answer…
- TechRadar AIagentsMCP for small businesses: How AI assistants can become your SMB marketing team
Mainstream AI news from a large tech publication.
- OpenAI NewsagentsGPT-6.1 Sol helps CodeRabbit strengthen security across complex codebases
CodeRabbit uses GPT-6.1 Sol to investigate security risks across complex codebases. Its security agent helps developers review findings and proposed fixes.
- LessWrongagentsA Descriptive Framework for Large Agent Systems (v0.1)
Author’s note: This is a working paper. If you notice something missing, contradictory, or broken, please let me know ! I will acknowledge or cite your contribution. When I do more work on the framework, I’ll update the…
- WIRED AIagentsMeet the AI Agents Trying to Be Real-Life Journalists
Jayden, Sam, and Zack are eagerly pitching editors on reported stories and investigative features. The catch? They're all AI agents.
- OpenAI NewsagentsHow Fanatics and OpenAI streamline the fan experience
Fanatics uses OpenAI to help fans complete their game-day outfits with Shop the Look. Testing across roughly 30,000 MLB products showed 10% higher engagement.
- arXiv cs.AIagentsPhronix: The Capability-Centric Learning Paradigm for Agents
arXiv:2610.31789v1 Announce Type: new Abstract: Scientific computing increasingly relies on large language model-based agents for performance engineering tasks such as instrumentation, analysis, and workflow porting. How…
- arXiv cs.AIagentsPaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
arXiv:2610.31810v2 Announce Type: replace Abstract: Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps au…
- arXiv cs.AIagentsDon't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons
arXiv:2610.31846v1 Announce Type: new Abstract: Intelligent agents should learn from their mistakes so that experience leads to continuous improvement. Yet today's agents recover from a mistake only temporarily: in-conte…
- arXiv cs.AIagentsTACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules
arXiv:2610.31882v1 Announce Type: new Abstract: We present the framework of TACS-RF - a Tool-driven Agentic Circuit Synthesis of RF and mmWave modules. In this framework, a large-language-model (LLM) coding agent (Claude…
- arXiv cs.AIagentsPermission to Retry: A Study of Authorization and Recovery in AI Agent Workflows
arXiv:2610.31916v1 Announce Type: new Abstract: A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of to…
- arXiv cs.AIagentsBeyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?
arXiv:2610.31918v1 Announce Type: new Abstract: Distilling interactive LLM agents requires choosing between teacher-generated demonstrations and student-generated experience, corresponding broadly to off-policy and on-po…
- arXiv cs.AIagentsKnowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation
arXiv:2610.31971v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly participate in negotiations on behalf of individuals and organizations, yet they remain vulnerable to manipulation, particula…
- arXiv cs.AIagentsReproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents
arXiv:2610.31972v1 Announce Type: new Abstract: Evaluating conversational agents that act on live, mutable enterprise data is hard: replayed sessions drift as backend state changes, and a benchmark built today can silent…