SOURCE-LINKED INTELLIGENCE

Sparks of In Silico Cognitive Science: Theories from Simulated Data Can Generalize to Humans

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Behavioral foundation models have been proposed as stand-ins for human participants across settings, but it is unclear whether theories discovered on them generalize to humans or merely characterize the simulator. We ran the Automated Cognitive Scientist (\textsc{AutoCog}), a closed-loop discovery system in which LLM agents design theory-discriminating experiments, collect responses, arbitrate between competing theories, and synthesize successors, entirely on behavior simulated by Centaur, a foundation model of human behavior. In a multi-attribute decision-making setting, the theories \textsc{

Read original source ↗ Open in workspace

recordType

paper

region

Global