@misc{zheng2025group, title={Group Sequence Policy Optimization}, author={Chujie Zheng and Shixuan Liu and Mingze Li and Xiong-Hui Chen and Bowen Yu and Chang Gao and Kai Dang and Yuqiong Liu and Rui Men and An Yang and Jingren Zhou and Junyang Lin}, year={2025}, eprint={2507.18071}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2507.18071} }