@article{internalizethetemperatureonpolicyselfdis,
  title = {Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning},
  author = {Xuewei Yang and Jiachen Yu and Jie Wu and Shaoning Sun and Junjie Wang and Yujiu Yang},
  year = {2026},
  eprint = {2606.00755},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.00755},
}