arXiv (All)
open access
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense token-level supervision. Existing methods usually assume trusted PI, such as reference answers or successful traces. We ask whether PI can instead com
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
- PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces#1014930
- Beyond Imitation: Reflective On-Policy Self-Distillation for LLM Reasoning#1129277
- Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling#1129359
- Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs#793700
- Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs#789696
Record · ID 926054
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