arXiv (All)
open access
OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation
Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learning (RL) addresses this issue by scoring open-ended responses against explicit criteria. However, because the reward is assigned after the complete response, the training signal does n
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
- ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training#1357295
- ReFlow: Replay-Driven Decoupling for Efficient RL Post-Training#1348821
- Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning#1342535
- Towards Better Training Signal: Advantage Clipped Policy Optimization#1132017
- Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models#1345094
Record · ID 1187095
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