Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
This work addresses the challenge of simulating human behavior in data-scarce urban environments, particularly for city sciences applications like mobility modeling, but it is incremental as it builds on existing generative agents and LLMs.
The paper tackled the problem of simulating realistic human behavior in urban environments by introducing the Preference Chain method, which integrates Graph RAG with LLMs to enhance context-aware simulation, and demonstrated that it outperforms standard LLMs in aligning with real-world transportation mode choices on the Replica dataset.
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.