AI ethics evidence index Search
Source-linked daily record
Evidence record 4441 · automatically gathered

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation (OPD) offers denser token-level supervision by training on student-generated trajectories, yet existing methods typically distill each rollout independently and ignore the other attempts sampled for the same prompt. We introduce Multi-Rollout On-Policy Distillation (MOPD), a pee

Record details

Published: 12 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Children & education
Retrieved: 14 July 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.

Shared topic: Regulation · Shared topic: Children & education

Eskwai for Students: Generative AI Assistant for Legal Education in Ghana

arXiv · 14 May 2026

Shared topic: Regulation · Shared topic: Children & education

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation

arXiv · 10 May 2026

Shared topic: Regulation · Shared topic: Children & education

Knowing the Rules Is Not Enough: Student Regulatory Awareness and Use of GenAI in Higher Education

arXiv · 16 May 2026

Shared topic: Regulation · Shared topic: Children & education

Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability

arXiv · 8 May 2026

Shared topic: Regulation · Shared topic: Children & education

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning

arXiv · 8 May 2026

Shared topic: Regulation · Shared topic: Children & education

SOD: Step-wise On-policy Distillation for Small Language Model Agents

arXiv · 8 May 2026

How to cite this record

ethics.ai (12 May 2026), “Multi-Rollout On-Policy Distillation via Peer Successes and Failures,” evidence record 4441, https://ethics.ai/record/4441 (originally published by arXiv).

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.