Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models.

arXiv:2605.06188v2 Announce Type: replace Abstract: On-Policy Self-Distillation (OPSD) has emerged as a promising post-training method: requiring only privileged context, it enables token-level credit assignment from a self-teacher with hindsight, yielding hig