@article{docpoadvancingdocumentpolicyoptimization,
  title = {DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards},
  author = {Yunhao Wang and Binghong Wu and Zhenyu Huang and Jiacheng Shi and Shuo Huang and Tinghao Yu and Feng Zhang},
  year = {2026},
  eprint = {2608.00536},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.00536},
}