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.

Citation

Repository: <a href="https://github.com/bibisbar/ReflectRL" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">GitHub - bibisbar/ReflectRL
Paper: <a href="https://huggingface.co/papers/2608.03972" target="_blank" rel="noopener noreferrer" class="text-blue-400 hover:text-blue-300 underline underline-offset-2 transition-colors">Hugging Face Papers

bibtex

@article{reflectrl2027,
  title={ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning},
  author={Jinhe Bi and Chennan Zhou and Zengjie Jin and Aniri and Shuo Lu and Wenke Huang and Hu Cao and Xun Xiao and Zhihong Zhu and Volker Tresp and Fei Shen and Yunpu Ma and Tat-Seng Chua},
  year={2026}
}

Jinhe/ReflectRL-Llama-3.1-8B-Instruct-GRPO-ReflectRL

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

Overview

Citation

Jinhe/
ReflectRL-Llama-3.1-8B-Instruct-GRPO-ReflectRL