Scaling Agent Learning via Experience Synthesis
Paper
• 2511.03773 • Published
• 82
agentic RL
Note for online RL training “提炼为经验模型”
-
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
Paper • 2511.21689 • Published • 125 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 228 -
Reinforcement Learning for Self-Improving Agent with Skill Library
Paper • 2512.17102 • Published • 36 -
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Paper • 2601.21558 • Published • 58