From Failure to Mastery: Generating Hard Samples for Tool-use Agents Paper • 2601.01498 • Published Jan 4 • 2
FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling Paper • 2510.24645 • Published Oct 28, 2025 • 11
view article Article Gaia2 and ARE: Empowering the community to study agents +9 clefourrier, gregmialz, mlcu, mortimerp9, XciD, tfrere, evijit, RomainFroger, dheeraj7596, CarolinePascal, upiter • Sep 22, 2025 • 134
Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution Paper • 2509.21072 • Published Sep 25, 2025 • 16
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models Paper • 2403.13372 • Published Mar 20, 2024 • 183
AWorld: Orchestrating the Training Recipe for Agentic AI Paper • 2508.20404 • Published Aug 28, 2025 • 39
Exploring Superior Function Calls via Reinforcement Learning Paper • 2508.05118 • Published Aug 7, 2025 • 1
AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving Paper • 2508.09889 • Published Aug 13, 2025 • 32
view article Article AWorld Multi-Agent System Hits #1 on GAIA Leaderboard chengle • Aug 7, 2025 • 27
FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement Paper • 2505.20192 • Published May 26, 2025 • 2
Shifting AI Efficiency From Model-Centric to Data-Centric Compression Paper • 2505.19147 • Published May 25, 2025 • 145