Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation
On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level rewards of reinforcement learning. This feedback comes from a teacher conditioned on a full reference solution unavailable to the student. The ref...
Rui Li, Li-Yang He, Zheng Zhang et al.
· 0 citations