AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsMOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents
arXiv:2610.29249v1 Announce Type: cross Abstract: Omni-modal assistants must remember not only what users say, but also what they show and convey. Existing long-term memory benchmarks are mostly text-and-image or report…
- arXiv cs.AIagentsMemory-Centric Continual Learning for AI Agents
arXiv:2610.29357v1 Announce Type: cross Abstract: Autonomous agents powered by foundation models can reason, plan, and use tools, but their fixed weights and context limits hinder sustained learning from experience over…
- arXiv cs.AIagentsBeyond Small Talk: Modeling Disclosure Trajectories in Human-AI Conversation
arXiv:2610.29413v1 Announce Type: cross Abstract: Recently, we see a rise in conversational agents as a form of social and emotional support, where disclosure will unfold over time. Yet, current evaluations of these agen…
- arXiv cs.AIagentsRegoMender: A Multi-agent Framework for Automated Rego Policy Repair
arXiv:2610.29456v1 Announce Type: cross Abstract: Policy-as-Code (PaC) has emerged as a foundational paradigm in cloud-native systems. However, repairing Rego policies remains challenging due to their strict syntax, decl…
- arXiv cs.AIagentsHarness Scaling for Generalizable Agentic Reinforcement Learning
arXiv:2610.29458v2 Announce Type: replace-cross Abstract: Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction.…
- arXiv cs.AIagentsRethinking Agentic Model Orchestration for Time Series Forecasting
arXiv:2610.29504v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) perform unevenly across forecasting tasks. Recent work uses agentic model orchestration (AMO) to select or combine TSFMs, often outp…
- arXiv cs.AIagentsThe Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction
arXiv:2610.29577v1 Announce Type: cross Abstract: Many learning systems are performative: once deployed, their predictions change the data distribution on which future models are trained. In multi-agent settings, this fe…
- arXiv cs.AIagentsFogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather
arXiv:2610.29618v1 Announce Type: cross Abstract: Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between train…
- arXiv cs.AIagentsToward Recursive Self-Improvement in Physical AI
arXiv:2610.29677v1 Announce Type: cross Abstract: Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which it improves. Recent digital agents test this idea by…
- arXiv cs.AIagentsRetrieval Augmented Generation Compositionality
arXiv:2610.29722v1 Announce Type: cross Abstract: Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmen…
- arXiv cs.AIagentsMemoryTax: The Bitter Lesson of Agent Memory
arXiv:2610.29823v1 Announce Type: cross Abstract: Agent memory systems such as Mem0 and Zep decide what to keep before any question arrives; coding agents keep the raw history and let the model search it with its own too…
- arXiv cs.AIagentsPAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit
arXiv:2610.29870v1 Announce Type: cross Abstract: Coding agents can invest substantial effort in repository exploration and testing yet still produce unsuccessful patches. Existing online steering methods review trajecto…
- arXiv cs.AIagentsFaultGene: LLM-Assisted Fault-Augmented Test Generation for Hardware-in-the-Loop Validation of Autonomous Driving Systems
arXiv:2610.29969v1 Announce Type: cross Abstract: Reliable validation of autonomous driving cyber-physical systems requires testing not only nominal driving behavior but also failures arising from faults in sensing and e…
- arXiv cs.AIagentsAgent Behavior Maps: Locating Agents by What They Would Do, Without Running Them
arXiv:2610.30014v1 Announce Type: cross Abstract: LLM agents with similar success rates can follow different action sequences. An Agent Behavior Map represents LLM-harness combinations using centered action log-likelihoo…
- arXiv cs.AIagentsWhat the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion
arXiv:2610.30026v1 Announce Type: cross Abstract: Enterprise agents act on documents. Before an agent can follow a policy, answer a compliance question or file a ticket, some ingestion layer must turn a Word file or PDF…
- arXiv cs.AIagentsSWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation
arXiv:2610.30047v1 Announce Type: cross Abstract: Coding agents are typically evaluated using one-shot, well-formulated prompts. Benchmarks such as SWE-bench use existing GitHub issues as input for a coding agent and eva…
- arXiv cs.AIagentsParallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization
arXiv:2610.30074v1 Announce Type: cross Abstract: Parallel AI agents can produce useful local edits yet degrade a shared solution when their edits are combined. We model this coordination problem as discrete block optimi…
- arXiv cs.AIagentsAsymmetric On-Policy Distillation Learns In-Context Exploration
arXiv:2610.30105v1 Announce Type: cross Abstract: Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Lear…
- arXiv cs.AIagentsMultimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use
arXiv:2610.30108v1 Announce Type: cross Abstract: Multimodal agents (MMAs) sustain interaction through reasoning, memory, tools, and feedback, most visibly as computer-use agents, while robotic systems (RSs) couple sensi…
- arXiv cs.AIagentsQuant-Arena: Benchmarking LLM Agents for Quantitative Trading Research
arXiv:2610.30113v1 Announce Type: cross Abstract: Quantitative research is an iterative loop: a researcher proposes a market hypothesis, implements it as an executable signal, tests it on historical data, and decides wha…
- arXiv cs.AIagents2-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
arXiv:2602.21889v4 Announce Type: replace Abstract: Prognostic predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we still la…
- arXiv cs.AIagentsLean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
arXiv:2606.06523v3 Announce Type: replace Abstract: Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LL…
- arXiv cs.AIagentsCTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations
arXiv:2608.12002v2 Announce Type: replace Abstract: While autonomous agents show promise for network operations, existing telecom troubleshooting evaluations fail to capture the partial observability and heterogeneity of…
- arXiv cs.AIagentsFrom Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities
arXiv:2608.26950v2 Announce Type: replace Abstract: Large Language Models (LLMs) are evolving from performing end-to-end mathematical reasoning to integrating agentic intelligence. However, most existing math benchmarks…
- arXiv cs.AIagentsAllocating Indivisible Goods to Strategic Agents: Pure Nash Equilibria and Fairness
arXiv:2109.08644v3 Announce Type: replace-cross Abstract: We consider the problem of fairly allocating a set of indivisible goods to a set of strategic agents with additive valuation functions. We assume no monetary tran…
- arXiv cs.AIagentsRemote Rowhammer Attack using Adversarial Observations on Federated Learning Clients
arXiv:2505.06335v3 Announce Type: replace-cross Abstract: Federated Learning (FL) has the potential for simultaneous global learning amongst a large number of parallel agents, enabling emerging AI systems to be trained a…
- arXiv cs.AIagentsEnergy-Based Transfer for Reinforcement Learning
arXiv:2506.16590v2 Announce Type: replace-cross Abstract: Reinforcement learning remains sample inefficient, particularly when agents must adapt over time to related but distinct tasks, as in continual learning settings.…
- arXiv cs.AIagentsDoes Centralized Learning Help Embodied Agents Coordinate, and When Can a Tabular Study Tell?
arXiv:2601.17454v3 Announce Type: replace-cross Abstract: Tabular studies are a common way to compare independent and centralized multi-agent learners, because they avoid function approximation. A natural expectation is…
- arXiv cs.AIagentsRuleSmith: Multi-Agent LLMs for Automated Game Balancing
arXiv:2602.06232v2 Announce Type: replace-cross Abstract: Game balancing is a longstanding challenge requiring repeated playtesting, expert intuition, and extensive manual tuning. We introduce RuleSmith, a framework that…
- arXiv cs.AIagentsSUDP: Secret-Use Delegation Protocol for Agentic Systems
arXiv:2604.24920v4 Announce Type: replace-cross Abstract: Agentic systems now act with user secrets for APIs, messaging platforms, and cloud services. Today's agent runtimes typically implement authorization by exposure:…
- arXiv cs.AIagentsDeep Reasoning in General Purpose Agents via Structured Meta-Cognition
arXiv:2605.11388v3 Announce Type: replace-cross Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through ass…
- arXiv cs.AIagentsBiological Context Does Not Reliably Improve LLM-Guided Experimental Optimization
arXiv:2605.15341v2 Announce Type: replace-cross Abstract: Autonomous labs increasingly deploy large language models (LLMs) as closedloop biology optimizers that propose a design, read the outcome, then propose again. Thi…
- arXiv cs.AIagentsClosing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDR
arXiv:2606.08168v2 Announce Type: replace-cross Abstract: Leading commercial endpoint detection and response (EDR) products have shifted from operator-configured rule sets to multi-component systems where autonomous AI c…
- arXiv cs.AIagentsASPIRE: Agentic /Skills Discovery for Robotics
arXiv:2607.00272v2 Announce Type: replace-cross Abstract: Traditional robot programming is notoriously challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling divers…
- The Verge AIagentsAI agents are ready to shop. Some retailers are wary
Using an AI agent to shop for you is a strange experience. Tech companies have marketed them as personal assistants - the democratizing of labor that ordinarily would only be available to the rich and powerful. In practi…
- OpenAI NewsagentsUber brings ChatGPT Work to all employees with OpenAI
Uber is rolling out ChatGPT Work to more than 30,000 employees, helping teams research, analyze data, create presentations, and complete complex workflows.
- AWS Machine Learning Blogagents5 production challenges in multi-agent systems and how Deep Insight solved them
Many teams build a multi-agent AI prototype in days but hit a wall in production. This post defines five production challenges (orchestration, per-agent model selection, reliable operation, secure code execution, and mon…
- AWS Machine Learning BlogagentsAdaptive agentic intelligence framework using Strands Agents
The Adaptive Agentic Intelligence Framework (AAIF), built with Strands Agents, handles routine tasks locally with small language models and routes complex requests to cloud models through Amazon Bedrock. This post walks…
- The Register AI + MLagentsReach new heights of laziness by burning tokens to let an AI tap your smartphone screen for you
Nothing will ruin your faith in humanity like an AI that operates your smartphone slowly, struggles with basic tasks, and can charge you for it
- The Verge AIagentsAnthropic takes on Muse with Claude Duet, its new AI agent
Anthropic just announced an AI agent competitor to Meta's Muse and OpenAI's Dots: Claude Duet. The new agent, designed for professionals and small business owners, is launching as a "research preview," according to Anthr…
- TechCrunch AIagentsWhile Amazon blocks AI agents, Walmart rolls out the welcome mat
As Amazon blocks AI agents from shopping on its site, Walmart is taking the opposite approach, introducing new technology that lets AI agents make purchases on customers' behalf, with controls over spending and transacti…
- The Verge AIagentsWalmart is inviting AI agents to shop for you
Walmart will soon let AI agents shop on its website for you. Next month, the retail giant will allow you to use an AI agent on the site, with systems in place to let you approve and review purchases and set spending limi…
- OpenAI NewsagentsHow AT&T is rethinking in-house legal work with OpenAI
AT&T is working with OpenAI to make legal knowledge easier to access. Learn how its LegalEdge team is rethinking intake and scaling legal judgment.
- SiliconANGLE AIagentsRed Hat and Nvidia expand their partnership to secure autonomous AI agents
Red Hat Inc. today expanded its collaboration with Nvidia Corp. to help enterprises secure autonomous artificial intelligence agents, govern access to AI models and deploy workloads on Nvidia’s upcoming Vera Rubin data c…
- Latent SpaceagentsClaude Mods: Flipping the Harness Inside Out
Claude Mods is an early form of the Attention Interface. It flips the agent harness paradigm from the harness facing the machine, to the harness facing the human.
- Latent SpaceagentsClaude Mods: Flipping the Harness Inside Out
Claude Mods is an early form of the Attention Interface. It flips the agent harness paradigm from the harness facing the machine, to the harness facing the human.
- Mistral AI NewsagentsMistral Advances AI for Engineering with NVIDIA
Mistral is collaborating with NVIDIA to develop a new generation of AI-native engineering workflows powered by NVIDIA accelerated computing.
- The Register AI + MLagentsNvidia picks OpenShell to tame AI gents
Give your agents freedom to do useful work by locking them down
- TechRadar AIagentsStop choosing the wrong Agentic AI use cases
Mainstream AI news from a large tech publication.
- Engadget AIagentsMark Zuckerberg says Meta is 'entering a new phase' with Muse
Zuckerberg expects the agent will generate more revenue per user than the company's apps.