REPRODUCING AND EXTENDING EXPERIMENTS IN BEHAVIORAL STRATEGY WITH LARGE LANGUAGE MODELS

Abstract

In this study, we propose LLM agents as a novel approach in behavioral strategy research, complementing simulations and laboratory experiments to advance our understanding of cognitive processes in decision-making. Specifically, we reproduce a human multi-trial laboratory experiment in behavioral strategy using large language model (LLM) generated agents and investigate how LLM agents compare to observed human behavior. Our findings suggest that LLMs may complement the methodological toolkit in behavioral strategy research by offering novel paths for theory building and the development of testable hypotheses for future research.