Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We first clarify the role of OPD as an exploration catalyst: it steers the student toward correct reasoning paths via dense token-level guidance, without expanding capability ceiling. We confirm this by showing that prompt diversity matters more than per-problem sampling numbers, and
Record details
Published: 14 July 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Regulation · Children & education
Retrieved: 17 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation
HuggingFace Daily Papers · 14 July 2026
AI avatars are reshaping society in China — the law is trying to catch up
Nature Machine Intelligence · 14 July 2026
From ethical principles to executable governance: A policy-as-code framework for trustworthy AI in higher education
Computers and Education: Artificial Intelligence · 14 July 2026
Understanding regional readiness to contribute to the bioeconomy: The role of higher education institutions and other regional characteristics
Research Policy · 14 July 2026
From AI anxiety to strategic regulation: How university students transform generative AI into a strategic learning resource
Computers and Education: Artificial Intelligence · 14 July 2026
Self-Regulated Reading with AI Support: An Eight-Week Study with Students
arXiv cs.CY · 15 July 2026
How to cite this record
ethics.ai (14 July 2026), “Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations,” evidence record 10992, https://ethics.ai/record/10992 (originally published by HuggingFace Daily Papers).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.