Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models

TL;DR

This paper introduces large language model (LLM) agents as a new method to replicate and extend behavioral strategy experiments, providing insights into decision-making processes and agent behavior.

Contribution

It demonstrates how LLM agents can reproduce human decision-making behavior and offers a novel approach for behavioral strategy research using AI models.

Findings

LLM agents effectively mimic human search and decision behaviors.

More forward-looking thoughts in LLMs correlate with exploitation over exploration.

The approach addresses limitations of traditional behavioral experiments.

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 laboratory experiment in behavioral strategy using large language model (LLM) generated agents and investigate how LLM agents compare to observed human behavior. Our results show that LLM agents effectively reproduce search behavior and decision-making comparable to humans. Extending our experiment, we analyze LLM agents' simulated "thoughts," discovering that more forward-looking thoughts correlate with favoring exploitation over exploration to maximize wealth. We show how this new approach can be leveraged in behavioral strategy research and address limitations.