arXiv (All)
open access
SCARL: Sequence Confidence-Aligned Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning by scoring sampled responses with a rule-based verifier and reinforcing those that pass. Where a classifier's training couples predicted probability to labels, nothing ties an RLVR policy's confidence in a respon
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
- SCARL: Sequence Confidence-Aligned Reinforcement Learning#1483011
- Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts#1129470
- Exploration via Activation-Space Steering for Reinforcement Learning with Verifiable Rewards#1402400
- Learned Reporting Preferences in RLVR Can Conflict with the Current Request#1131788
- Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners#1357045
Record · ID 1492015
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