arXiv (All)
open access
Mitigating the Length-Scaling Tax with Online Distillation
Length scaling during reinforcement-learning (RL) post-training is often viewed as a sign of improved reasoning ability, especially on difficult problems, but may also make responses to already-solved problems unnecessarily verbose. We quantify this side effect as the length-scaling tax (LST): exces
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
- Does Scaling Reinforcement Learning Really Require More Training?#1156068
- Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling#1129359
- Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation#216828
- SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation#1131943
- An Analysis of Self-supervised Pre-training with Dependent Samples#971986
Record · ID 1143455
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