@article{multirolloutonpolicydistillationviapeers, title = {Multi-Rollout On-Policy Distillation via Peer Successes and Failures}, author = {Weichen Yu and Xiaomin Li and Yizhou Zhao and Xiaoze Liu and Ruowang Zhang and Haixin Wang and Yinyi Luo and Chen Henry Wu and Gaurav Mittal and Matt Fredrikson and Yu Hu}, year = {2026}, eprint = {2605.12652}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.12652}, }