# TaxAI: A Dynamic Economic Simulator and Benchmark for Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2309.16307 · HTML: https://mlsanity.com/paper/2309.16307/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2023.

## Built on by (most cited first, 8 of 8)

- [MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework](https://mlsanity.com/paper/2504.21582/) (2025)
- [Simulating the Economic Impact of Rationality through Reinforcement Learning and Agent-Based Modelling](https://mlsanity.com/paper/2405.02161/) (2024)
- [EconGym: A Scalable AI Testbed with Diverse Economic Tasks](https://mlsanity.com/paper/2506.12110/) (2025)
- [PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training](https://mlsanity.com/paper/2509.06053/) (2025)
- [Repairing Reward Functions with Feedback to Mitigate Reward Hacking](https://mlsanity.com/paper/2510.13036/) (2025)
- [Learning Macroeconomic Policies through Dynamic Stackelberg Mean-Field Games](https://mlsanity.com/paper/2403.12093/) (2024)
- [When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation](https://mlsanity.com/paper/2512.24145/) (2025)
- [From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models](https://mlsanity.com/paper/2608.06020/) (2026)

## Abstract (arXiv)

Taxation and government spending are crucial tools for governments to promote economic growth and maintain social equity. However, the difficulty in accurately predicting the dynamic strategies of diverse self-interested households presents a challenge for governments to implement effective tax policies. Given its proficiency in modeling other agents in partially observable environments and adaptively learning to find optimal policies, Multi-Agent Reinforcement Learning (MARL) is highly suitable for solving dynamic games between the government and numerous households. Although MARL shows more potential than traditional methods such as the genetic algorithm and dynamic programming, there is a lack of large-scale multi-agent reinforcement learning economic simulators. Therefore, we propose a MARL environment, named TaxAI, for dynamic games involving N households, government, firms, and financial intermediaries based on the Bewley-Aiyagari economic model. Our study benchmarks 2 traditional economic methods with 7 MARL methods on TaxAI, demonstrating the effectiveness and superiority of MARL algorithms. Moreover, TaxAI's scalability in simulating dynamic interactions between the government and 10,000 households, coupled with real-data calibration, grants it a substantial improvement in scale and reality over existing simulators. Therefore, TaxAI is the most realistic economic simulator for optimal tax policy, which aims to generate feasible recommendations for governments and individuals.