# aiframeresearch/spo **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/aiframeresearch-spo).** 53 stars ยท 7 forks ยท Python ยท MIT ## Links - GitHub: https://github.com/AIFrameResearch/SPO - Homepage: https://arxiv.org/abs/2505.23564 - awesome-repositories: https://awesome-repositories.com/repository/aiframeresearch-spo.md ## Description ๐Ÿš€ Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models ๐ŸŒŸ ## Tags ### Part of an Awesome List - [Dense Reward Optimization](https://awesome-repositories.com/f/awesome-lists/ai/dense-reward-optimization.md) โ€” Segment-level credit assignment for reinforcement learning. - [Off-Policy Optimization](https://awesome-repositories.com/f/awesome-lists/ai/off-policy-optimization.md) โ€” Online off-policy reinforcement learning for sequence models.