arXiv (All)
open access
What RL Brings to Reasoning: A Few Decisions the Base Model Would Not Make
Reinforcement learning with verifiable rewards (RLVR) substantially improves mathematical reasoning, but what it adds to the base model remains unclear. We investigate this through a sequence of generation-time interventions on Qwen3-4B-Base, measuring how much of its RL-trained counterpart's gain e
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
- What are Key Factors for Updates in RL for LLM Reasoning?#1036727
- Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning#998621
- ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning#793014
- ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning#789010
Record · ID 1389609
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