ReflectRL Qwen2.5 Math 7B GRPO ReflectRL

--- license: apache-2.0 library_name: transformers pipeline_tag: text-generation base_model: Qwen/Qwen2.5-Math-7B --- # ReflectRL This model checkpoint is part of **ReflectRL**, presented in the paper [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972). - **Code & Repository:** [GitHub - ReflectRL](https://github.com/bibisbar/ReflectRL) - **Base Model:** [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) - **Paper:** [ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning](https://huggingface.co/papers/2608.03972) ## Overview 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 ```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={2027} } ```

Source context: 27 downloads · 0 likes · Pipeline text-generation · Library transformers · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL

Source context: 189 downloads · 0 likes · Repo Jinhe/ReflectRL-Qwen2.5-Math-7B-GRPO-ReflectRL