Scaling Agent Learning via Experience Synthesis
Paper • 2511.03773 • Published • 83
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 • 126 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 230 -
Reinforcement Learning for Self-Improving Agent with Skill Library
Paper • 2512.17102 • Published • 42 -
ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas
Paper • 2601.21558 • Published • 60 -
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning
Paper • 2511.22570 • Published • 93