Agent Learning via Early Experience
Paper • 2510.08558 • Published • 276
Agent
-
-
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Paper • 2510.08002 • Published • 24 -
Self-Improving LLM Agents at Test-Time
Paper • 2510.07841 • Published • 10 -
The Denario project: Deep knowledge AI agents for scientific discovery
Paper • 2510.26887 • Published • 8 -
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Paper • 2509.02547 • Published • 238 -
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research
Paper • 2509.13312 • Published • 106 -
LIMI: Less is More for Agency
Paper • 2509.17567 • Published • 104 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 84 -
VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
Paper • 2509.01055 • Published • 81 -
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
Paper • 2511.16043 • Published • 110 -
Scaling Agent Learning via Experience Synthesis
Paper • 2511.03773 • Published • 83 -
From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence
Paper • 2511.18538 • Published • 304 -
QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining
Paper • 2602.07085 • Published • 190 -
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 630 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 291 -
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Paper • 2604.06132 • Published • 121 -
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Paper • 2604.01658 • Published • 55 -
Neural Computers
Paper • 2604.06425 • Published • 31 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 108 -
Heterogeneous Scientific Foundation Model Collaboration
Paper • 2604.27351 • Published • 218 -
FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
Paper • 2604.25135 • Published • 12 -
The Last Harness You'll Ever Build
Paper • 2604.21003 • Published • 5 -
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Paper • 2604.22748 • Published • 227 -
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 274 -
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
Paper • 2604.22446 • Published • 121 -
The Last Human-Written Paper: Agent-Native Research Artifacts
Paper • 2604.24658 • Published • 21 -
SkillOS: Learning Skill Curation for Self-Evolving Agents
Paper • 2605.06614 • Published • 46 -
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
Paper • 2605.05724 • Published • 15 -
A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
Paper • 2605.06200 • Published • 14 -
Self-Distilled Agentic Reinforcement Learning
Paper • 2605.15155 • Published • 111 -
STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?
Paper • 2605.06527 • Published • 44 -
ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
Paper • 2605.15198 • Published • 19 -
Orchard: An Open-Source Agentic Modeling Framework
Paper • 2605.15040 • Published • 19 -
Dynamic Latent Routing
Paper • 2605.14323 • Published • 4 -
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 185 -
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
Paper • 2605.19769 • Published • 81 -
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
Paper • 2605.11609 • Published • 195 -
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
Paper • 2605.20668 • Published • 12 -
MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
Paper • 2605.19330 • Published • 8 -
QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks
Paper • 2605.24218 • Published • 41 -
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
Paper • 2605.23204 • Published • 29 -
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Paper • 2605.26086 • Published • 23 -
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Paper • 2605.23986 • Published • 17 -
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
Paper • 2605.24426 • Published • 10 -
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
Paper • 2605.23491 • Published • 9 -
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Paper • 2605.28774 • Published • 86 -
AI Research Agents Narrow Scientific Exploration
Paper • 2605.27905 • Published • 25 -
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
Paper • 2605.27908 • Published • 6 -
AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems
Paper • 2605.27466 • Published • 8 -
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
Paper • 2605.26457 • Published • 6 -
Advancing Creative Physical Intelligence in Large Multimodal Models
Paper • 2605.26396 • Published • 19 -
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Paper • 2605.28655 • Published • 11 -
GenClaw: Code-Driven Agentic Image Generation
Paper • 2605.30248 • Published • 36 -
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning
Paper • 2605.28424 • Published • 30 -
When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems
Paper • 2605.30102 • Published • 14 -
τ_0-WM: A Unified Video-Action World Model for Robotic Manipulation
Paper • 2606.01027 • Published -
OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
Paper • 2606.02031 • Published • 15 -
Joint Agent Memory and Exploration Learning via Novelty Signals
Paper • 2606.01528 • Published • 12 -
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Paper • 2605.30723 • Published • 13 -
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Paper • 2605.28556 • Published • 60 -
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Paper • 2606.02373 • Published • 36 -
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories
Paper • 2606.01311 • Published • 27 -
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
Paper • 2605.24202 • Published • 14