arXiv||1 min read
ChunkAct: Action Chunking for Agentic Robotics
Focuses on ChunkAct: Action Chunking for Agentic Robotics.
Topic archive
AI Agents AI news
AI agents, coding assistants, tool use, and agent workflows. This page collects the latest briefings that match the topic so readers can follow one area without scanning the full feed.
Indexed briefings
1508
Latest source-linked updates, ordered newest first.
Latest
Recent briefings
arXiv||1 min read
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
Focuses on Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards.
arXiv||1 min read
EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence
Focuses on EmbodiedEvo: Self-improving Coding Agents for Physical Intelligence.
arXiv||1 min read
AutoAgent0: An Agentic Runtime for Safe Closed-Loop Driving
Focuses on AutoAgent0: An Agentic Runtime for Safe Closed-Loop Driving.
arXiv||1 min read
Hybrid Reasoning Agents
Focuses on Hybrid Reasoning Agents.
OpenAI||1 min read
The EU’s next chapter in AI is agentic
New analysis shows how agentic AI adoption is growing across EU enterprises and small businesses—and where deeper use could unlock more value.
arXiv||1 min read
Self-Evolving Agent Harness
Focuses on Self-Evolving Agent Harness.
arXiv||1 min read
Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning
Focuses on Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning.
arXiv||1 min read
SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection
Focuses on SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection.
arXiv||1 min read
SEAR: Self-Evolving Agentic Robotics
Focuses on SEAR: Self-Evolving Agentic Robotics.
arXiv||1 min read
Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Response
Focuses on Trust Before Autonomy: Rethinking Agentic Remote Sensing for Crisis Response.
arXiv||1 min read
Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
Focuses on Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents.
arXiv||1 min read
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
Focuses on BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems.
arXiv||1 min read
Beyond the Verdict: Agentic Code Judging with Verifiable Feedback
Focuses on Beyond the Verdict: Agentic Code Judging with Verifiable Feedback.
Meta AI||1 min read
Introducing Muse Wonder and Muse Wonder Full: Frontier Models for Agents
Meta is introducing Muse Wonder and Muse Wonder Full, our most capable models to date, built to deliver state-of-the-art performance on personal and professional agentic...
arXiv||1 min read
Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark
Focuses on Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark.
arXiv||1 min read
RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
Focuses on RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics.
arXiv||1 min read
X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
Focuses on X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems.
arXiv||1 min read
BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation
Focuses on BT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity Evaluation.
arXiv||1 min read
Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
Focuses on Returning to Development States: When Full Sandbox Snapshots Help Coding Agents.
arXiv||1 min read
MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
Focuses on MC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents.
arXiv||1 min read
Matched-Context Group Policy Optimization for LLM Agent Training
Focuses on Matched-Context Group Policy Optimization for LLM Agent Training.
arXiv||1 min read
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
Focuses on SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning.
arXiv||1 min read
What 30,000 Hours of Ego-centric Video Does Not Teach
Focuses on What 30,000 Hours of Ego-centric Video Does Not Teach.
arXiv||1 min read
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
Focuses on From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents.
arXiv||1 min read
BrickBench: Evaluating Agentic Brick Design
Focuses on BrickBench: Evaluating Agentic Brick Design.
arXiv||1 min read
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
Focuses on Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff.
arXiv||1 min read
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
Focuses on OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video.
arXiv||1 min read
SciExam for ENSO: Can AI Agents Build Climate Models?
Focuses on SciExam for ENSO: Can AI Agents Build Climate Models?.
arXiv||1 min read
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills
Focuses on ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills.
arXiv||1 min read
Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies
Focuses on Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies.
arXiv||1 min read
OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport
Focuses on OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport.
arXiv||1 min read
Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
Focuses on Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models.
arXiv||1 min read
AgentGarten: Code Worlds for Evolving Agents
Focuses on AgentGarten: Code Worlds for Evolving Agents.
arXiv||1 min read
A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
Focuses on A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents.
arXiv||1 min read
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
Focuses on Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict.