@article{stabilizingreinforcementlearningwithllms,
  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 Hao Lin and Chencan Wu and Feng Hu and An Yang and Jingren Zhou and Junyang Lin},
  year = {2025},
  eprint = {2512.01374},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.01374},
}