arXiv (All)
open access
Learning from Think-Mode Advantage via On-Policy Distillation
Explicit intermediate reasoning gives large language models (LLMs) a stronger problem-solving mode. We study learning from this think-mode advantage via on-policy distillation (OPD). OPD preserves student-generated trajectories and provides dense token-level teacher targets at student-visited prefix
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
- DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation#1070478
- When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation#820519
- Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning#467105
- Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning#1129277
- An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning#1130086
Record · ID 1132245
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