@article{surgicalposttrainingproximalonpolicydist, title = {Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention}, author = {Wenye Lin and Kai Han}, year = {2026}, eprint = {2603.01683}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.01683}, }