Consumption and Savings with Large Language Model Agents

Michael R Douglas, Sergiy Verstyuk

Abstract: In a canonical consumption-savings model with aggregate productivity and individual employment risk, standard fully rational agents evaluate contingencies and make decisions by following prescriptions from economic theory. This paper replaces them with agents whose intelligence and behavior are powered by Large Language Models, richly parameterized neural networks trained on vast amounts of text. The performance of such LLM agents is in many ways more similar to that of capable but imperfect human beings than their perfectly rational theoretical counterparts. They demonstrate reasonable economic behavior coupled with systematic anthropomorphic biases in their decisions and beliefs. The linguistic capabilities of LLMs also permit extensive inter-agent communication. The general approach is additionally validated in a game-theoretic setting.