# A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis

arXiv: https://arxiv.org/abs/2502.16879 · HTML: https://mlsanity.com/paper/2502.16879/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 2 of its 14 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 2 of 2)

- [Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games](https://mlsanity.com/paper/2410.21359/) (2024)
- [How Different AI Chatbots Behave? Benchmarking Large Language Models in Behavioral Economics Games](https://mlsanity.com/paper/2412.12362/) (2024)

## Built on by (most cited first, 11 of 11)

- [DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios](https://mlsanity.com/paper/2510.15501/) (2025)
- [Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets](https://mlsanity.com/paper/2510.25779/) (2025)
- [Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs](https://mlsanity.com/paper/2506.00577/) (2025)
- [EconGym: A Scalable AI Testbed with Diverse Economic Tasks](https://mlsanity.com/paper/2506.12110/) (2025)
- [Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making](https://mlsanity.com/paper/2511.12876/) (2025)
- [MALLES: A Multi-agent LLMs-based Economic Sandbox with Consumer Preference Alignment](https://mlsanity.com/paper/2603.17694/) (2026)
- [AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation](https://mlsanity.com/paper/2603.24736/) (2026)
- [Soft-Label Governance for Distributional Safety in Multi-Agent Systems](https://mlsanity.com/paper/2604.19752/) (2026)
- [Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM](https://mlsanity.com/paper/2609.04738/) (2026)
- [LLM Agents as Computational Typologists](https://mlsanity.com/paper/2609.07791/) (2026)
- [From Preference to Reciprocity: Decentralized Matching with Empirically Grounded LLM-agent Based Modeling](https://mlsanity.com/paper/2609.34679/) (2026)

## Abstract (arXiv)

This paper pioneers a novel approach to economic and public policy analysis by leveraging multiple Large Language Models (LLMs) as heterogeneous artificial economic agents. We first evaluate five LLMs' economic decision-making capabilities in solving two-period consumption allocation problems under two distinct scenarios: with explicit utility functions and based on intuitive reasoning. While previous research has often simulated heterogeneity by solely varying prompts, our approach harnesses the inherent variations in analytical capabilities across different LLMs to model agents with diverse cognitive traits. Building on these findings, we construct a Multi-LLM-Agent-Based (MLAB) framework by mapping these LLMs to specific educational groups and corresponding income brackets. Using interest-income taxation as a case study, we demonstrate how the MLAB framework can simulate policy impacts across heterogeneous agents, offering a promising new direction for economic and public policy analysis by leveraging LLMs' human-like reasoning capabilities and computational power.