Discovering Differences in Strategic Behavior between Humans and LLMs

Caroline Wang, Daniel Kasenberg, Kim Stachenfeld, Pablo Samuel Castro

Keywords: large language models, behavioral game theory, strategic behavior, cognitive science, computational social science

TL;DR: A comparison of human and LLM strategic behavior by comparing behavioral models discovered by AlphaEvolve.

Abstract: As Large Language Models (LLMs) are increasingly deployed in social and strategic scenarios, it becomes critical to understand where and why their behavior diverges from that of humans. While behavioral game theory (BGT) provides a framework for analyzing behavior, existing models do not fully capture the idiosyncratic behavior of humans or black-box, non-human agents like LLMs. We employ AlphaEvolve, a cutting-edge program discovery tool, to directly discover *interpretable* models of human and LLM behavior from data, thereby enabling open-ended discovery of structural factors driving human and LLM behavior. Our analysis on iterated rock-paper-scissors reveals that frontier LLMs can be capable of deeper strategic behavior than humans. These results provide a foundation for understanding structural differences driving differences in human and LLM behavior in strategic interactions.

Paper Type: New Full Paper

Submission Number: 20