Saved in:
Bibliographic Details
Main Authors: Hu, Kai, Atchade-Adelomou, Parfait, Adornetto, Carlo, Mora-Carrero, Adrian, Alonso-Pastor, Luis, Noyman, Ariel, Liu, Yubo, Larson, Kent
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.16172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915479988207616
author Hu, Kai
Atchade-Adelomou, Parfait
Adornetto, Carlo
Mora-Carrero, Adrian
Alonso-Pastor, Luis
Noyman, Ariel
Liu, Yubo
Larson, Kent
author_facet Hu, Kai
Atchade-Adelomou, Parfait
Adornetto, Carlo
Mora-Carrero, Adrian
Alonso-Pastor, Luis
Noyman, Ariel
Liu, Yubo
Larson, Kent
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16172
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
Hu, Kai
Atchade-Adelomou, Parfait
Adornetto, Carlo
Mora-Carrero, Adrian
Alonso-Pastor, Luis
Noyman, Ariel
Liu, Yubo
Larson, Kent
Artificial Intelligence
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.
title Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
topic Artificial Intelligence
url https://arxiv.org/abs/2508.16172