AI-based Problem Solving and Planning

This study demonstrates that large language models can design, execute, and revise experiments autonomously using a robotic system.

The paper investigates how humans adaptively use cognitive resources in problem-solving tasks requiring different planning depths, finding they select minimum required depths rather than fixed depths.

This paper introduces a Bayesian model of hierarchy discovery that explains how humans organize environments into hierarchical structures for planning, supported by simulations and behavioral experiments.