@article{unleashingimplicitrewardsprefixvaluelear,
  title = {Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization},
  author = {Shiping Gao and Hongzhan Chen and Xiaojun Quan and Qifan Wang and Lifu Huang},
  year = {2026},
  eprint = {2604.13197},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.13197},
}