AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsAsking Less, Adapting Better: Feedback-Efficient Test-Time Adaptation for Vision-and-Language Navigation
arXiv:2610.30643v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires agents to follow instructions and navigate to target locations. However, current VLN agents often suffer severe performance…
- arXiv cs.AIagentsThe Delegation Divide: An Open Index of AI-Agent Delegability across Occupations and Countries
arXiv:2610.30752v1 Announce Type: cross Abstract: 35.2% of task time in world employment is at least partly delegable to AI agents in 2026, and only 2.5% can be handed over in full. Existing measures score exposure to ge…
- arXiv cs.AIagentsAbstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses
arXiv:2610.30763v1 Announce Type: cross Abstract: AI assistants built on large language models (LLMs) are trained on human feedback and increasingly personalized to users' stated preferences. Yet how closely these prefer…
- arXiv cs.AIagentsFolding Pooled Usage Examples into the Tool Index Lowers Retrieval of Unused Tools
arXiv:2610.30867v2 Announce Type: replace-cross Abstract: AI agents often find tools by searching their documentation. Agents that share a tool catalog can also pool usage examples: past requests, each tagged with the to…
- arXiv cs.AIagentsTruthful by Omission: Click Thinning for LLM-Native Advertising
arXiv:2610.30999v1 Announce Type: cross Abstract: Generative AI assistants are becoming an advertising medium, embedding sponsored content in their answers. This setting departs from classical position auctions in two wa…
- arXiv cs.AIagentsProductWebBench: Evaluating Website Continuity Beyond Task Completion
arXiv:2610.31118v1 Announce Type: cross Abstract: Frontend coding agents are usually graded on one question: did the requested target get built. Real engineering changes carry a second obligation, because the rest of the…
- arXiv cs.AIagentsMemory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
arXiv:2610.31272v1 Announce Type: cross Abstract: Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily pr…
- arXiv cs.AIagentsBeyond Accuracy: Disentangling Decomposition from Typed-State Quality Assurance in Multi-Agent LLM Pipelines
arXiv:2610.31280v1 Announce Type: cross Abstract: Multi-agent LLM pipelines are often credited with gains in software engineering tasks, but it is rarely clear whether a gain stems from the typed contract between agents…
- arXiv cs.AIagentsSuperintelligent Software Engineering: Governance That Scales with Capability
arXiv:2610.31306v2 Announce Type: replace-cross Abstract: Software agents are being trained to exceed human engineers; we argue that capability alone does not produce better software engineering. We define superintellige…
- arXiv cs.AIagentsAgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments
arXiv:2610.31326v1 Announce Type: cross Abstract: Evolutionary program search with large language models keeps the structure of an evolutionary algorithm and uses the model as its variation operator. Typically, the model…
- arXiv cs.AIagentsAutomating Feature Flag Cleanup at Scale with Multi-Agent LLM Systems: An Industrial Experience at DoorDash
arXiv:2610.31351v1 Announce Type: cross Abstract: Feature flags are runtime configuration mechanisms used for gradual feature rollouts, experimentation, and kill switches. Once a feature is fully rolled out, the flag and…
- arXiv cs.AIagentsAgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
arXiv:2610.31404v1 Announce Type: cross Abstract: Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing therefore poses privac…
- arXiv cs.AIagentsTraining Small Language Models for Transferable Tool Selection
arXiv:2610.31483v1 Announce Type: cross Abstract: As LLM agents operate over corpora of more than ten thousand tools, selecting the right tool for a complex multi-step user instruction becomes a central bottleneck. Tool…
- arXiv cs.AIagentsQuestioning Instrumental Convergence in RLVR: Checkpoint Evidence from OLMo-3
arXiv:2610.31624v1 Announce Type: cross Abstract: Instrumental convergence is often invoked as a general reason to expect capable agents to acquire or express power-seeking subgoals: self-preservation, resource acquisiti…
- arXiv cs.AIagentsMETTA: Memory-Enhanced Test-Time Adaptation for Meta-Reinforcement Learning
arXiv:2610.31656v1 Announce Type: cross Abstract: Meta-reinforcement learning aims to train agents that adapt quickly to unseen tasks from limited interaction, but this requires representing task evidence over long inter…
- arXiv cs.AIagentsCLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
arXiv:2604.07487v3 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineering approaches primar…
- arXiv cs.AIagentsSkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
arXiv:2605.14089v2 Announce Type: replace Abstract: In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration…
- arXiv cs.AIagentsMLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
arXiv:2606.06473v2 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained se…
- arXiv cs.AIagentsManimAgent: Self-Evolving Multimodal Agents for Visual Education
arXiv:2606.30296v3 Announce Type: replace Abstract: Multi-round reflection lets agents built on large language models recover from failures within a single task, but each task remains an isolated episode: lessons learned…
- arXiv cs.AIagentsHow Far Can Root Cause Analysis Go on Real-World Telemetry Data?
arXiv:2607.13548v2 Announce Type: replace Abstract: Root cause analysis (RCA) of microservice failures requires reasoning over telemetry far larger than a model's context, so a language agent reasons over extracted evide…
- arXiv cs.AIagentsEvaluating Rational Contracting in Natural Language
arXiv:2608.10475v2 Announce Type: replace Abstract: The emergence of language-based AI agents promises to transform the scope of machine economic activity. Instead of just proposing bids or following hard-coded protocols…
- arXiv cs.AIagentsFrom Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
arXiv:2608.10502v2 Announce Type: replace Abstract: Persistent memory lets language model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter r…
- arXiv cs.AIagentsTRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
arXiv:2608.16156v2 Announce Type: replace Abstract: Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactio…
- arXiv cs.AIagentsOptimistic Policy Regularization: Elite-Statistic Reward Shaping
arXiv:2603.06793v2 Announce Type: replace-cross Abstract: On-policy agents discard trajectories after each update, including rare high-return episodes. We propose Optimistic Policy Regularization (OPR), which turns those…
- arXiv cs.AIagentsMeasuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
arXiv:2604.04978v3 Announce Type: replace-cross Abstract: Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthro…
- arXiv cs.AIagentsStop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits
arXiv:2605.18890v2 Announce Type: replace-cross Abstract: The scientific claims drawn from LLM social simulations should be no stronger than the robustness audits that support them. Generative agents bring new expressive…
- arXiv cs.AIagentsHow Far Will They Go? Red-Teaming Online Influence with Large Language Models
arXiv:2605.22880v2 Announce Type: replace-cross Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming their capacity to support political influence campaigns is cr…
- arXiv cs.AIagentsPerceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
arXiv:2606.12830v2 Announce Type: replace-cross Abstract: While recent vision-language models (VLMs) demonstrate strong multimodal understanding, they remain limited in spatial reasoning tasks that require active evidenc…
- arXiv cs.AIagentsRobustness Verification of an Autonomous Underwater Vehicle-based Plankton Classifier
arXiv:2607.04453v2 Announce Type: replace-cross Abstract: The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous un…
- arXiv cs.AIagentsARES: Adaptive Reasoning-Effort Steering for PPA- and Cost-Aware RTL Optimization with LLM Agents
arXiv:2607.27879v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents optimize the power, performance, and area (PPA) of register-transfer-level (RTL) designs by iterating over edits, synthesis, and…
- arXiv cs.AIagentsPrinciples of Robot Autonomy
arXiv:2608.03496v2 Announce Type: replace-cross Abstract: Autonomous robots are moving rapidly from research labs into everyday life - on roads, in the air, in warehouses, and in space. Robot autonomy is no longer solely…
- TechCrunch AIagentsUber rival inDrive eyes 2027 robotaxi tests in Central Asia with Pony AI and Nvidia
The company plans to begin testing Pony.ai's robotaxis in Kazakhstan's capital in the first half of 2027.
- Hugging Face BlogagentsTurning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
Open-source model releases, tooling, and community updates.
- TechCrunch AIagents1Password launches a way for AI agents to log in on your behalf without seeing your password
The new feature allows agents to log into a customer's personal accounts while still protecting the private credentials that secure those accounts.
- The DecoderagentsMajor US banks are locking out AI agents that log in with customer credentials
Customers are letting AI agents use their credentials to access accounts at Morgan Stanley, JPMorgan, and other major U.S. banks, sometimes without direct instructions. Morgan Stanley has blocked agents, while other bank…
- The Verge AIagentsIn Meta’s version of the future, I’ll have my Muse call your Muse
Mark Zuckerberg is barrelling toward a future in which an autonomous network of AI agents will run our lives - shopping for us, working for us, talking to other people's AI agents for us. Are humans ready for this very s…
- AWS Machine Learning BlogagentsHow IskayPet unified corporate knowledge with Amazon Bedrock Managed Knowledge Bases
Learn how IskayPet, a leading pet care company in Iberia, built a multilingual corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases. The assistant answers employee questions across retail, veterinary,…
- The DecoderagentsGoogle's Agent Compute Engine gives every Gemini agent its own hardware-isolated micro virtual machine
With Agent Compute Engine, Google is introducing a runtime environment designed specifically for AI agents, while also expanding the governance capabilities that enable companies to manage agents in cloud, hybrid, and on…
- AWS Machine Learning BlogagentsStream low-latency speech from AI agents using Kokoro TTS on Amazon SageMaker AI
Voice agents often wait for an agent's full response before starting speech synthesis, adding latency users feel directly. This post shows how to stream each sentence to a Kokoro-82M text-to-speech model on Amazon SageMa…
- SiliconANGLE AIagentsIBM puts governed context at the center of production AI
Governed context is becoming a practical requirement for artificial intelligence agents expected to make decisions across a business. As enterprises move beyond personal productivity tools, those agents need information…
- AWS Machine Learning BlogagentsHow Rescale built an AI triage agent with Strands Agents and AI-DLC
Rescale used the AI-Driven Development Lifecycle (AI-DLC) framework on AWS, with Strands Agents and Amazon Bedrock, to build an intelligent test-triage agent in weeks. Learn how AI-DLC structures AI-assisted development…
- TechCrunch AIagentsUber puts all 30,000 employees on ChatGPT Work
The ride-share giant previously deployed a much smaller pilot for ChatGPT Work but is now taking the enterprise agent company-wide.
- Microsoft ResearchagentsFlint-interactive: A language for creating interactive data visualizations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interac…
- TechCrunch AIagentsSpotify’s current AI bet is about being the music service that agents choose
Spotify co-CEO Gustav Söderström explains why the rise of AI agents could be good news for the music service.
- LessWrongagentsThe Alignment Journal: Our Approach and Related Projects
The Alignment Journal is now open for submissions! This is the fifth post in a series: the announcement post introduced the journal's core premise and its three key innovations: paid attributed review, published review s…
- Latent SpaceagentsThe Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi
How Moshi turns market data into actionable insights, and why AI tools have to fit the trader’s workflow.
- Latent SpaceagentsYou are the Team — Anekha Sokhal, Moshi
How Moshi turns market data into actionable insights, and why AI tools have to fit the trader’s workflow.
- TechCrunch AIagentsClaude Duet app is Anthropic’s bet on agents
Claude Duet is available through waitlist for Pro and Max plan users.
- SiliconANGLE AIagentsAnthropic introduces Claude Duet, a proactive AI agent for professionals
Anthropic PBC Wednesday introduced Claude Duet, a proactive artificial intelligence agent for professionals and small business owners in research preview, which completes tasks when asked, keeps working behind the scenes…
- Ben's BitesagentsClaude’s personal agent
And how I run the newsletter with agents