SOURCE-LINKED INTELLIGENCE

On-policy Distillation with Verifiable Reward

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RLVR suffers from sparse task-level feedback, while OPD provides dense token-level guidance but ignores trajectory correctness, limiting its performance to that of the teacher. Combining them is a promising direction: OPD supplies dense supervisory signals, while RLVR provides task-level correctness. Nevertheless, existing integrations often rely on weighted combination or heuristic switching, introducing extra hyperpa

Read original source ↗ Open in workspace

recordType

paper

region

Global