cs.LGFeb 9, 2026

Reasoning under uncertainty in humans and language models

Authors: Gonçalo Guiomar, Elia Torre, Victoria Shavina, Pehuen Moure, Mario Giulianelli, Shih-Chii Liu, Valerio Mante

Organizations: Equal contribution · ETH AI Center, Zürich, Switzerland · Institute for Neuroinformatics, University of Zürich & ETH Zürich, Switzerland · ETH Zürich, Switzerland · 

Abstract

Do language models make decisions under uncertainty like humans do? And if so, what role does extended reasoning play in the underlying decision process? We answer this question by introducing an active probabilistic reasoning task that cleanly separates sampling (actively acquiring evidence) from inference (integrating evidence towards a decision). Benchmarking humans and a broad set of contemporary LLMs against an optimal reference policy reveals a consistent pattern: extended reasoning is the key determinant of strong performance, driving large gains in inference, while yielding only modest improvements in active sampling. To explain these differences, we fit a behavioral model that captures systematic deviations from optimal Bayesian behavior through interpretable parameter families, placing humans and models in a shared low-dimensional cognitive space. The resulting fits show how reasoning shifts models toward human-like regimes of evidence accumulation and belief-to-choice mapping, and yield testable predictions about the latent dynamics that might drive each decision. Probing residual-stream activations of an open-weight reasoning model, we find that the geometry of internal representations tracks these predicted dynamics, linking behavior to representational correlates of the fitted latent dynamics.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. How Uncertainty Estimation Scales with Sampling in Reasoning Models

    Mar 19, 2026Maksym Del, Markus Kängsepp, Marharyta Domnich +4LLM Uncertainty EstimationUncertainty Quantification

  2. Tracing the ongoing emergence of human-like reasoning in Large Language Models

    May 20, 2026Paolo Morosi, Nikoleta Pantelidou, Fritz Günther +2Logical ReasoningPragmatic Reasoning in Language Models

  3. Humans and LLMs Diverge on Probabilistic Inferences

    Feb 26, 2026Gaurav Kamath, Sreenath Madathil, Sebastian Schuster +2LLM Reasoning