ZPPO: Teacher-in-Prompts Knowledge Distillation Outperforms Gradient Methods for Small Reasoners

Zone of Proximal Policy Optimization (ZPPO, arXiv 2606.18216) embeds teacher guidance in prompts rather than gradients: it constructs prompts pairing correct teacher responses with incorrect student responses for contrastive learning, and prompts aggregating student errors to surface failure patterns. Tested on 0.8B–9B student models with a 27B teacher, ZPPO outperforms distillation and RL baselines, with strongest gains for smaller models.