@article{everyquestionhasitsownvaluereinforcement,
  title = {Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values},
  author = {Dian Yu and Yulai Zhao and Kishan Panaganti and Linfeng Song and Haitao Mi and Dong Yu},
  year = {2025},
  eprint = {2510.20187},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.20187},
}