EP346: Teaching small AI to ignore teachers

Title: Reward-Gated On-Policy DistillationSource: http://arxiv.org/abs/2607.04037v1Summary:This paper proposes a novel on-policy distillation method that gates token-level teacher supervision using sparse verifier feedback to prevent the propagation of incorrect reasoning modes. It represents a significant optimization breakthrough for transferring complex reasoning capabilities from frontier models to smaller student models.