@article{restmctsllmselftrainingviaprocess,
  title = {ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search},
  author = {Dan Zhang and Sining Zhoubian and Ziniu Hu and Yisong Yue and Yuxiao Dong and Jie Tang},
  year = {2024},
  eprint = {2406.03816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.03816v3},
}