@misc{zheng2025stabilizing,
  title={Stabilizing Reinforcement Learning with LLMs: Formulation and Practices},
  author={Chujie Zheng and Kai Dang and Bowen Yu and Mingze Li and Huiqiang Jiang and Junrong Lin and Yuqiong Liu and An Yang and Jingren Zhou and Junyang Lin},
  year={2025},
  eprint={2512.01374},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2512.01374}
}