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

2026-09-07

AI Summary

研究使用AutoCog系统通过模拟数据发现理论，并验证这些理论能否泛化到人类行为，结果显示模拟中发现的理论在人类数据上表现良好。

Abstract

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{AutoCog} found on Centaur generalized to human data: they outperformed canonical theories on ten held-out experiments and were rivaled only by theories found by running the same loop on people. We argue that this succeeds despite the simulator's inevitable imperfections because a discovery loop that arbitrates between competing theories demands less of its simulator than estimation does. The simulator only needs to capture the regularities that distinguish the theories, and not necessarily reproduce behavior precisely. Imperfect simulators can therefore widen the search over theories, with human data then testing whether the surfaced theories generalize.

Problem

• behavioral foundation models
• theory generalization
• simulated data
• human behavior

Innovation

• Automated Cognitive Scientist
• behavioral foundation models
• theory generalization
• closed-loop discovery system
• multi-attribute decision-making