TaxAgent: How Large Language Model Designs Fiscal Policy
This research addresses economic inequality for policymakers by providing a scalable, data-driven framework for fiscal policy evaluation, though it appears incremental as it builds on existing methods like agent-based modeling and LLMs.
The study tackled the problem of economic inequality by designing adaptive tax policies using TaxAgent, which integrates large language models with agent-based modeling, achieving superior equity-efficiency trade-offs compared to benchmarks like Saez Optimal Taxation and U.S. federal income taxes.
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.