Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?

TL;DR

This paper explores whether large language models can generate agent behaviors in financial markets that align with traditional heterogeneous agent models, revealing promising similarities and systematic biases.

Contribution

It introduces a generative agent built with an LLM that models strategy adoption probabilities, bridging AI expectations with established economic models.

Findings

AI expectations align with HAM literature for S&P 500 (1990-2020)

Artificial market data confirms heterogeneity in expectations

Systematic bias toward fundamentalist behavior in AI agents

Abstract

Results in the Heterogeneous Agent Model (HAM) literature determine the proportion of fundamentalists and trend followers in the financial market. This proportion varies according to the periods analyzed. In this paper, we use a large language model (LLM) to construct a generative agent (GA) that determines the probability of adopting one of the two strategies based on current information. The probabilities of strategy adoption are compared with those in the HAM literature for the S\&P 500 index between 1990 and 2020. Our findings suggest that the resulting artificial intelligence (AI) expectations align with those reported in the HAM literature. At the same time, extending the analysis to artificial market data helps us to filter the decision-making process of the AI agent. In the artificial market, results confirm the heterogeneity in expectations but reveal systematic asymmetry toward the fundamentalist behavior.