OPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models
arXiv:2605.06188v1 Announce Type: cross
Abstract: On-Policy Self-Distillation (OPSD) has recently emerged as an alternative to Reinforcement Learning with Verifiable Rewards (RLVR), promising higher accuracy and shorter responses through token-level c…