@article{rethinkingonpolicydistillationoflargelan, title = {Rethinking On-Policy Distillation of Large Language Models II: One Training Example}, author = {Zixuan Fu and Bingxiang He and Yuxin Zuo and Haohuan Huang and Jinqian Zhang and Ruhang Xiao and Cheng Qian and Qinyu Luo and Huan-ang Gao and Yudong Wang and Zhiyuan Liu and Ning Ding and Chaojun Xiao}, year = {2026}, eprint = {2609.04172}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2609.04172}, }