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

2025-08-22

AI Summary

Emerging urban areas suffer from scarce human mobility data, and existing LLM-based agents struggle to generate consistent, context-aware travel behavior. Method: This paper proposes a mobile agent framework grounded in Preference Chains, integrating graph-structured Retrieval-Augmented Generation (Graph RAG), large language models, and behavioral chain reasoning to model fine-grained, interpretable travel mode choices on the Replica dataset. Contribution/Results: The framework explicitly encodes human mobility preferences as learnable, chain-structured representations and dynamically injects urban spatial context via graph retrieval—effectively alleviating generalization bottlenecks under data scarcity. Compared to standard LLM baselines, it achieves significant improvements in both accuracy and consistency on real-world travel decision-making tasks. This work establishes a novel paradigm for urban transportation forecasting in low-data regimes.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Knowledge Representation and Reasoning: Preferences
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Simulating realistic human behavior in urban transport systems
• Addressing data scarcity in newly developed urban areas
• Improving context-aware behavioral outputs using Graph RAG

Innovation

• Graph RAG with LLMs integration
• Preference Chain for context-aware simulation
• Mobility Agent for urban modeling