@article{reducingbeliefdeviationinreinforcementle,
  title = {Reducing Belief Deviation in Reinforcement Learning for Active Reasoning},
  author = {Deyu Zou and Yongqiang Chen and Jianxiang Wang and Haochen Yang and Mufei Li and James Cheng and Pan Li and Yu Gong},
  year = {2025},
  eprint = {2510.12264},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.12264},
}