@misc{wang2024offline,
  title={Offline Reinforcement Learning for LLM Multi-Step Reasoning},
  author={Huaijie Wang and Shibo Hao and Hanze Dong and Shenao Zhang and Yilin Bao and Ziran Yang and Yi Wu},
  year={2024},
  eprint={2412.16145},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2412.16145}
}