@article{grouprelativereinforceissecretlyanoffpol, title = {Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends}, author = {Chaorui Yao and Yanxi Chen and Yuchang Sun and Yushuo Chen and Wenhao Zhang and Xuchen Pan and Yaliang Li and Bolin Ding}, year = {2025}, eprint = {2509.24203}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.24203}, }