@article{pruneopdefficientandreliableonpolicydist, title = {Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning}, author = {Zhicheng Yang and Zhijiang Guo and Yifan Song and Minrui Xu and Yongxin Wang and Yiwei Wang and Xiaodan Liang and Jing Tang}, year = {2026}, eprint = {2605.07804}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.07804}, }