arXiv · 2026 · Preprint

Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention

Wenye Lin, Kai Han

Date
2026-03-02
Citations
1
arXiv
2603.01683
Cite
@misc{lin2026surgical,
  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},
}