@article{serlselfplayreinforcementlearningfor,
  title = {SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data},
  author = {Wenkai Fang and Shunyu Liu and Yang Zhou and Kongcheng Zhang and Tongya Zheng and KaiXuan Chen and Mingli Song and DaCheng Tao},
  year = {2025},
  eprint = {2505.20347},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.20347v1},
}