Evidence record 17336 · automatically gathered

DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level. On-policy self-distillation (OPSD) mitigates this sparsity by querying a privileged teacher at student-visited prefixes and providing dense token-level distributional supervision. Although this dense supervision alleviates signal sparsity, we find that standard OPSD stil

Record details

Published: 6 August 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation · Children & education
Retrieved: 7 August 2026

source-onlyevidence status

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.

How to cite this record

ethics.ai (6 August 2026), “DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models,” evidence record 17336, https://ethics.ai/record/17336 (originally published by arXiv cs.AI).

JSON

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.