exgrpo-learning-from-experience

【数据与研究】Improve LLM reasoning efficiency by systematically reusing past rollouts through experience replay. ExGRPO organizes training data by success and diversity, applying a mixed-policy objective that prioritizes high-quality examples while maintaining exploration, achieving 3.5-7.6 point gains over on-policy methods.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准