@article{dvpodistributionalvaluemodelingbasedpoli, title = {DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training}, author = {Dingwei Zhu and Zhiheng Xi and Shihan Dou and Yuhui Wang and Sixian Li and Junjie Ye and Honglin Guo and Shichun Liu and Chenhao Huang and Yajie Yang and Junlin Shang and Senjie Jin and Ming Zhang and Jiazheng Zhang and Caishuang Huang and Yunke Zhang and Yuran Wang and Tao Gui}, year = {2025}, eprint = {2512.03847}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2512.03847}, }