AI RESEARCH
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
arXiv CS.LG
•
ArXi:2605.19436v1 Announce Type: new When a model produces a correct solution under reinforcement learning with verifiable rewards (RLVR), every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler. A natural fix is to condition the model on the correct answer as a teacher, identifying tokens it would have generated differently had it known the answer. Prior work shows this either corrupts