works on
bandit tasks 1decision making 1exploration 1large language models 1metacognition 1uncertainty 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.LG2026

Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models

Hua-Dong Xiong, Xinyuan Yan, Ji-An Li +3

The paper investigates how large language models think under uncertainty by testing them on two-armed bandit tasks, measuring action preferences, thinking duration, and confidence,…