3,694 items tracked: 32 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2608.22055v3 Announce Type: replace Abstract: Embodied language-model agents must coordinate interdependent actions while each holds private task information.
arXiv:2609.01038v2 Announce Type: replace Abstract: A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement.
arXiv:2609.04518v2 Announce Type: replace Abstract: Recent systems train coding agents with reinforcement learning (RL) on trajectories collected through multiple execution harnesses.
arXiv:2511.01047v4 Announce Type: replace-cross Abstract: Automated program repair (APR) has recently shifted toward large language models and agent-based systems, while prior work shows that repository history can help…
arXiv:2603.03753v2 Announce Type: replace-cross Abstract: The ongoing shift of Artificial Intelligence (AI) from centralized cloud application programming interfaces (APIs) to local inference on edge devices is enabling…
arXiv:2604.07900v2 Announce Type: replace-cross Abstract: Industrial anomaly generation is a crucial method for alleviating the data scarcity problem in anomaly detection tasks.
arXiv:2605.10268v2 Announce Type: replace-cross Abstract: Long-context reasoning tasks have motivated agent-memory approaches that process document chunks sequentially while maintaining a dynamically updated memory, avoi…
arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA).
arXiv:2606.16215v2 Announce Type: replace-cross Abstract: Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns.
arXiv:2606.19386v2 Announce Type: replace-cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a mode…
arXiv:2606.21496v2 Announce Type: replace-cross Abstract: Deploying generalist robotic agents in the real world requires transferable skills.
arXiv:2607.22724v2 Announce Type: replace-cross Abstract: Group-based policy optimization has been increasingly used to train large language model (LLM) agents from sparse outcome rewards by comparing trajectories or ste…
arXiv:2608.09524v2 Announce Type: replace-cross Abstract: Incident response planning is critical for restoring compromised software systems.
arXiv:2609.01487v2 Announce Type: replace-cross Abstract: Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steer…
arXiv:2610.12542v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that could refute it - giv…
arXiv:2610.12917v1 Announce Type: new Abstract: AI shopping assistants increasingly influence which products consumers consider.
arXiv:2610.12747v1 Announce Type: cross Abstract: Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and systematic evaluation…
arXiv:2610.13439v1 Announce Type: cross Abstract: Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes that benefit AVs may…
arXiv:2603.07427v3 Announce Type: replace Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based s…
arXiv:2608.29460v3 Announce Type: replace Abstract: When coding agents encounter defective test infrastructure they may reward-hack: hardcoding outputs or editing test files to pass tests they cannot legitimately satisfy…
arXiv:2601.18783v3 Announce Type: replace-cross Abstract: A central difficulty in applying reinforcement learning to real-world applications such as autonomous driving is that conventional scalar reward formulations obta…
arXiv:2605.19469v2 Announce Type: replace-cross Abstract: Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world.
arXiv:2606.27045v2 Announce Type: replace-cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve:…
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window.
I'm diving into agentic coding loops to get my organization to automerge more.
The feature is explained below: The user enters a search query: E.g.
There’s no question that 2026 is the year of the artificial intelligence agent.
Teams of AI agents barely outperform solo agents but cost up to 5.1x more, according to Vals AI.
Epoch AI and Anthropic independently found the same thing: current AI models like GPT-5.6 Sol and Claude Fable 5 can run experiments but lack scientific self-criticism and genuine creative thinking.
Most traditional enterprise systems were built around three assumptions: Jobs finish quickly, retrying one is free and the same input always produces the same output.
Meanwhile, AI agents move robotic arms, 'make OT device operator screens lie'
We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.
In its latest report, Anthropic has revealed that its AI agents meddled with government websites during testing.
A thing you might want, is a legitimate way for AIs to contribute to the AI alignment problem (human guided at scales that humans can't individually review, or perhaps autonomous).
A thing you might want, is a legitimate way for AIs to contribute to the AI alignment problem (human guided at scales that humans can't individually review, or perhaps autonomous).
Anthropic detailed the activity of its A.I.
Enterprise AI orchestration must account for agents working across the data, applications and infrastructure businesses already use.
At this year's OpenAI DevDay, CEO Sam Altman unveiled the company's new AI agent Dots - and told the crowd that the company wants to "set a new standard for privacy in frontier AI." OpenAI would spend the day taking veil…
Study finds coding efficiency gains get “absorbed” by human review “bottleneck.”
Tokens transmitted in metadata, weak VM isolation, and expansive permissions make hacking a lot easier
In case you haven’t heard, the rogue AI agents are here.
Amazon says it will stop using NDAs when negotiating data center deals with local governments, following a similar move from Microsoft earlier this year.
A monthly recap of the latest Amazon Bedrock, Amazon Bedrock AgentCore, and Strands updates from September 2026: broader model choice, faster serverless agents with built-in evaluation, and automated knowledge base synci…
Building an AI agent that works in a demo is a different problem from running one for 40 million developers.
Analysts welcome Fusion Claw's tighter controls but warn of early adoption and cloud lock-in
AI agents have made identity the front line of enterprise security.