Can Generative AI agents behave like humans? Evidence from laboratory market experiments

TL;DR

This study investigates whether Large Language Models can mimic human economic behavior in market experiments, finding they replicate broad trends but lack some behavioral diversity, highlighting their potential and limitations.

Contribution

It introduces a dynamic feedback market simulation with LLMs, demonstrating their ability to emulate certain human behaviors and market trends in economic experiments.

Findings

LLMs display bounded rationality similar to humans.

Memory of three previous steps improves LLM behavior alignment.

LLMs show less behavioral heterogeneity than humans.

Abstract

We explore the potential of Large Language Models (LLMs) to replicate human behavior in economic market experiments. Compared to previous studies, we focus on dynamic feedback between LLM agents: the decisions of each LLM impact the market price at the current step, and so affect the decisions of the other LLMs at the next step. We compare LLM behavior to market dynamics observed in laboratory settings and assess their alignment with human participants' behavior. Our findings indicate that LLMs do not adhere strictly to rational expectations, displaying instead bounded rationality, similarly to human participants. Providing a minimal context window i.e. memory of three previous time steps, combined with a high variability setting capturing response heterogeneity, allows LLMs to replicate broad trends seen in human experiments, such as the distinction between positive and negative feedback markets. However, differences remain at a granular level--LLMs exhibit less heterogeneity in behavior than humans. These results suggest that LLMs hold promise as tools for simulating realistic human behavior in economic contexts, though further research is needed to refine their accuracy and increase behavioral diversity.