ReflectRL-Qwen2.5-3B-Instruct-GRPO-ReflectRL

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

This repository contains the model checkpoint for ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning.

ReflectRL is a lightweight framework for learning from Golden Negative Trajectories (GNTs) during on-policy post-training. Instead of imitating failed expert trajectories directly, ReflectRL uses them as reflective context during training and gradually transitions the policy back to direct reasoning for inference.

• Paper: ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
• Repository: GitHub - ReflectRL

Citation

@article{reflectrl2027,
  title={ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning},
  author={Bi, Jinhe and Zhou, Chennan and Jin, Zengjie and Aniri and Lu, Shuo and Huang, Wenke and Cao, Hu and Xiao, Xun and Zhu, Zhihong and Tresp, Volker and Shen, Fei and Ma, Yunpu and Chua, Tat-Seng},
  year={2027}
}