Simulating Macroeconomic Expectations using LLM Agents

TL;DR

This paper presents a new framework using LLM Agents to simulate macroeconomic expectations, demonstrating their human-like reasoning and potential to enhance economic modeling and AI behavioral science.

Contribution

It introduces a modular LLM Agent framework that replicates survey experiments and provides insights into designing AI agents with human-like economic expectations.

Findings

LLM Agents produce more homogeneous expectations than humans.

They outperform simple prompt-engineered LLMs.

Their capabilities are driven by specific architectural components.

Abstract

We introduce a novel framework for simulating macroeconomic expectations using LLM Agents. By constructing LLM Agents equipped with various functional modules, we replicate three representative survey experiments involving several expectations across different types of economic agents. Our results show that although the expectations simulated by LLM Agents are more homogeneous than those of humans, they consistently outperform LLMs relying simply on prompt engineering, and possess human-like mental mechanisms. Evaluation reveals that these capabilities stem from the contributions of their components, offering guidelines for their architectural design. Our approach complements traditional methods and provides new insights into AI behavioral science in macroeconomic research