arXiv (All)
open access
Verifier-Induced Support Reshaping in On-Policy Optimization
We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce. We call this verifier-induced support reshaping and define effective rewardable support as successfu
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
- RPS: Information Elicitation with Reinforcement Prompt Selection#14045
- RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses#149102
- Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR#1154382
- Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVR#1136873
- CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards#975238
Record · ID 1141619
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