@misc{sang2026onpolicyselfdistillationreasoningcompression,
title={On-Policy Self-Distillation for Reasoning Compression},
author={Hejian Sang and Yuanda Xu and Zhengze Zhou and Ran He and Zhipeng Wang and Jiachen Sun},
year={2026},
eprint={2603.05433},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2603.05433},
}