@article{directvalueoptimizationimprovingchainof,
  title = {Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values},
  author = {Hongbo Zhang and Han Cui and Guangsheng Bao and Linyi Yang and Jun Wang and Yue Zhang},
  year = {2025},
  eprint = {2502.13723},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.13723v1},
}