Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Albert, Daniel, Billinger, Stephan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910642165776384
author Albert, Daniel
Billinger, Stephan
author_facet Albert, Daniel
Billinger, Stephan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06932
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models
Albert, Daniel
Billinger, Stephan
General Economics
Economics
Artificial Intelligence
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.
title Reproducing and Extending Experiments in Behavioral Strategy with Large Language Models
topic General Economics
Economics
Artificial Intelligence
url https://arxiv.org/abs/2410.06932