SOURCE-LINKED INTELLIGENCE

What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric mechanisms in OPD remain relatively underexplored. This paper presents a empirical study of data efficiency and data selection in OPD. We begin by investigating an extreme setting: training OPD on only one example, namely 1-shot OPD. Surprisingly, we find that 1-shot OPD is consistently effective across all sampled training examples and harder examples often yield superior performance gain. We next investigate what actually driv

Read original source ↗ Open in workspace

recordType

paper

region

Global