Reasoning & Test-Time Compute · 2025
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Shows via pass@k that RLVR mainly sharpens sampling of solutions already reachable by the base model rather than expanding its reasoning boundary, reframing what current reasoning-RL actually buys.
Editorial record
Plain-language summary
Shows via pass@k that RLVR mainly sharpens sampling of solutions already reachable by the base model rather than expanding its reasoning boundary, reframing what current reasoning-RL actually buys.
Knowledge graph
Relationships
Descendants
Conceptual ancestorEvidence: Strongly supported
Chain-of-Thought Prompting Elicits Reasoning
Builds on the reasoning lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-642
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2504.13837
- arXiv:2504.13837
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.