@article{dreamtochatmodelbasedreinforcementlearni,
  title = {Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling},
  author = {Yue Zhao and Xiaoyu Wang and Dan Wang and Zhonglin Jiang and Qingqing Gu and Teng Chen and Ningyuan Xi and Jinxian Qu and Yong Chen and Luo Ji},
  year = {2025},
  eprint = {2508.16876},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.16876},
}