TaxAgent: How Large Language Model Designs Fiscal Policy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jizhou, Fang, Xiaodan, Huang, Lei, Huang, Yongfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909635037888512
author Wang, Jizhou
Fang, Xiaodan
Huang, Lei
Huang, Yongfeng
author_facet Wang, Jizhou
Fang, Xiaodan
Huang, Lei
Huang, Yongfeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02838
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TaxAgent: How Large Language Model Designs Fiscal Policy
Wang, Jizhou
Fang, Xiaodan
Huang, Lei
Huang, Yongfeng
Artificial Intelligence
General Economics
Economics
I.2.11; I.6.5; J.4
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.
title TaxAgent: How Large Language Model Designs Fiscal Policy
topic Artificial Intelligence
General Economics
Economics
I.2.11; I.6.5; J.4
url https://arxiv.org/abs/2506.02838