Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain

TL;DR

This paper presents the Preference Chain, a novel method combining Graph RAG and LLMs to improve context-aware human behavior simulation in urban transportation, especially in data-scarce environments.

Contribution

The paper introduces the Preference Chain, a new approach integrating Graph RAG with LLMs to enhance realistic and consistent behavioral simulations in urban mobility modeling.

Findings

Preference Chain outperforms standard LLM in real-world transportation choice alignment.

Demonstrates potential for urban mobility modeling, personalized travel analysis, and traffic forecasting.

Highlights limitations like slow inference and hallucination risks.

Abstract

Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. To address these limitations, this paper introduces the Preference Chain, a novel method that integrates Graph Retrieval-Augmented Generation (RAG) with LLMs to enhance context-aware simulation of human behavior in transportation systems. Experiments conducted on the Replica dataset demonstrate that the Preference Chain outperforms standard LLM in aligning with real-world transportation mode choices. The development of the Mobility Agent highlights potential applications of proposed method in urban mobility modeling for emerging cities, personalized travel behavior analysis, and dynamic traffic forecasting. Despite limitations such as slow inference and the risk of hallucination, the method offers a promising framework for simulating complex human behavior in data-scarce environments, where traditional data-driven models struggle due to limited data availability.