TaxAgent: How Large Language Model Designs Fiscal Policy

TL;DR

This paper presents TaxAgent, an innovative framework combining large language models with agent-based modeling to design adaptive, data-driven fiscal policies that better address economic inequality and taxpayer heterogeneity.

Contribution

Introduction of TaxAgent, a novel LLM-based agent system for dynamic tax policy optimization, outperforming traditional models in equity and efficiency trade-offs.

Findings

TaxAgent outperforms Saez Optimal Taxation and U.S. federal taxes in simulations.

The framework effectively balances equity and productivity.

TaxAgent provides a scalable, data-driven approach for fiscal policy design.

Abstract

Economic inequality is a global challenge, intensifying disparities in education, healthcare, and social stability. Traditional systems like the U.S. federal income tax reduce inequality but lack adaptability. Although models like the Saez Optimal Taxation adjust dynamically, they fail to address taxpayer heterogeneity and irrational behavior. This study introduces TaxAgent, a novel integration of large language models (LLMs) with agent-based modeling (ABM) to design adaptive tax policies. In our macroeconomic simulation, heterogeneous H-Agents (households) simulate real-world taxpayer behaviors while the TaxAgent (government) utilizes LLMs to iteratively optimize tax rates, balancing equity and productivity. Benchmarked against Saez Optimal Taxation, U.S. federal income taxes, and free markets, TaxAgent achieves superior equity-efficiency trade-offs. This research offers a novel taxation solution and a scalable, data-driven framework for fiscal policy evaluation.