SimCity: Multi-Agent Urban Development Simulation with Rich Interactions

2025-10-01

AI Summary

Traditional equilibrium models struggle to capture agent heterogeneity, while existing agent-based models (ABMs) rely on hand-crafted rules, compromising interpretability and empirical fidelity. To address these limitations, this paper proposes the first multi-agent urban simulation framework integrating large language models (LLMs) and vision-language models (VLMs). The framework employs LLM-driven natural language reasoning to enable adaptive decision-making by heterogeneous economic agents—households, firms, and government—in labor, goods, and financial markets; concurrently, VLMs generate dynamic spatial urban maps, enabling, for the first time, unified modeling of macroeconomic regularities and urban expansion within a single environment. Experiments successfully reproduce canonical empirical phenomena—including price and demand elasticity, Engel’s law, and Okun’s law—demonstrating the model’s robustness and explanatory power. This work establishes a novel paradigm for macro-spatial coupled modeling.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Large Language Models (LLMs) open new possibilities for constructing realistic and interpretable macroeconomic simulations. We present SimCity, a multi-agent framework that leverages LLMs to model an interpretable macroeconomic system with heterogeneous agents and rich interactions. Unlike classical equilibrium models that limit heterogeneity for tractability, or traditional agent-based models (ABMs) that rely on hand-crafted decision rules, SimCity enables flexible, adaptive behavior with transparent natural-language reasoning. Within SimCity, four core agent types (households, firms, a central bank, and a government) deliberate and participate in a frictional labor market, a heterogeneous goods market, and a financial market. Furthermore, a Vision-Language Model (VLM) determines the geographic placement of new firms and renders a mapped virtual city, allowing us to study both macroeconomic regularities and urban expansion dynamics within a unified environment. To evaluate the framework, we compile a checklist of canonical macroeconomic phenomena, including price elasticity of demand, Engel's Law, Okun's Law, the Phillips Curve, and the Beveridge Curve, and show that SimCity naturally reproduces these empirical patterns while remaining robust across simulation runs.

Problem

• Modeling macroeconomic systems with heterogeneous agents
• Enabling adaptive agent behavior through natural-language reasoning
• Studying urban expansion dynamics within unified simulation environment

Innovation

• Uses LLMs for adaptive macroeconomic agent behavior
• Integrates VLM for geographic urban expansion modeling
• Combines multiple markets within unified simulation environment