@article{tokenlevelpolicyoptimizationlinkinggroup,
  title = {Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood},
  author = {Xingyu Lin and Yilin Wen and En Wang and Du Su and Wenbin Liu and Chenfu Bao and Zhonghou Lv},
  year = {2025},
  eprint = {2510.09369},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.09369},
}