AI RESEARCH
How Uncertainty Estimation Scales with Sampling in Reasoning Models
arXiv CS.AI
•
ArXi:2603.19118v1 Announce Type: new Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box approach using verbalized confidence and self-consistency. Across three reasoning models and 17 tasks spanning mathematics, STEM, and humanities, we characterize how these signals scale.