arXiv (All)
open access
Prompt Breadth and Rollout Refresh Interact in On-Policy Distillation
How many prompts does on-policy distillation (OPD) need, and how does the answer depend on the student policies that generate its training responses? We study these two controls jointly: prompt breadth and rollout refresh. A 3x3 mathematical-reasoning experiment fixes 14,080 trajectories and 110 opt
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning#620733
- Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning#619054
- What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection#660869
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?#629949
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?#628087
Record · ID 1051541
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive