arXiv (All)
open access
Where Groups Split: A Probe Prior for Nonzero Within-Group Variance in RL Post-Training
Group relative policy optimization learns from a prompt only when the rewards in the sampled group disagree. With a binary verifier, a group that is entirely correct or entirely incorrect has within-group variance zero and a zero advantage. Uniform sampling continues to spend rollouts on prompts tha
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
- Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO#1142319
- Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO#1122303
- F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare#925105
- F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare#920871
- Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval#1037563
Record · ID 1400155
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