@inproceedings{ijcai2025p61,
  title     = {Indirect Online Preference Optimization via Reinforcement Learning},
  author    = {Wang, En and Lin, Xingyu and Su, Du and Bao, Chenfu and Lv, Zhonghou and Yang, Funing and Xu, Yuanbo and Liu, Wenbin},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {538--546},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/61},
  url       = {https://doi.org/10.24963/ijcai.2025/61},
}