arXiv (All)
open access
P^2O: Joint Policy and Prompt Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but is suffer from advantage collapse: when all rollouts of a query receive identical rewards, the group variance vanishes, most damagingly on hard samples, where scaling rollout budgets yields little
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
- From Base Rollouts to RL Reasoning: A Budgeted Search Perspective#821227
- Diversifying RLVR Rollouts via First-Token Exploration#1141250
- Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning#1132267
- Skip What You Can Predict: Predictive Repositioning for Policy Optimization for Efficient LLM Training#1128591
- ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning#1131454
Record · ID 1128571
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