Hua-Tuo Cao

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning

ReflectRL is proposed, a lightweight plug-and-play framework that learns from Golden Negative Trajectories during on-policy training, and first uses these trajectories to elicit Reflective Reasoning, then applies Reflective-to-Direct Policy Transition to transfer the acquired reasoning behavior back to Direct Reasoning...