Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Chenjie, Jiang, Yutian, Liang, Anqi, Qi, Wei, Wu, Chenyu, Zhang, Junbo
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.05529
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917397903966208
author Yang, Chenjie
Jiang, Yutian
Liang, Anqi
Qi, Wei
Wu, Chenyu
Zhang, Junbo
author_facet Yang, Chenjie
Jiang, Yutian
Liang, Anqi
Qi, Wei
Wu, Chenyu
Zhang, Junbo
contents Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regions where historical trajectories are unavailable or restricted. To bridge this gap, we propose \textbf{ActivityEditor}, a novel dual-LLM-agent framework designed for zero-shot cross-regional trajectory generation. Our framework decomposes the complex synthesis task into two collaborative stages. Specifically, an intention-based agent, which leverages demographic-driven priors to generate structured human intentions and coarse activity chains to ensure high-level socio-semantic coherence. These outputs are then refined by editor agent to obtain mobility trajectories through iteratively revisions that enforces human mobility law. This capability is acquired through reinforcement learning with multiple rewards grounded in real-world physical constraints, allowing the agent to internalize mobility regularities and ensure high-fidelity trajectory generation. Extensive experiments demonstrate that \textbf{ActivityEditor} achieves superior zero-shot performance when transferred across diverse urban contexts. It maintains high statistical fidelity and physical validity, providing a robust and highly generalizable solution for mobility simulation in data-scarce scenarios. Our code is available at: https://anonymous.4open.science/r/ActivityEditor-066B.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05529
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
Yang, Chenjie
Jiang, Yutian
Liang, Anqi
Qi, Wei
Wu, Chenyu
Zhang, Junbo
Artificial Intelligence
Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regions where historical trajectories are unavailable or restricted. To bridge this gap, we propose \textbf{ActivityEditor}, a novel dual-LLM-agent framework designed for zero-shot cross-regional trajectory generation. Our framework decomposes the complex synthesis task into two collaborative stages. Specifically, an intention-based agent, which leverages demographic-driven priors to generate structured human intentions and coarse activity chains to ensure high-level socio-semantic coherence. These outputs are then refined by editor agent to obtain mobility trajectories through iteratively revisions that enforces human mobility law. This capability is acquired through reinforcement learning with multiple rewards grounded in real-world physical constraints, allowing the agent to internalize mobility regularities and ensure high-fidelity trajectory generation. Extensive experiments demonstrate that \textbf{ActivityEditor} achieves superior zero-shot performance when transferred across diverse urban contexts. It maintains high statistical fidelity and physical validity, providing a robust and highly generalizable solution for mobility simulation in data-scarce scenarios. Our code is available at: https://anonymous.4open.science/r/ActivityEditor-066B.
title ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
topic Artificial Intelligence
url https://arxiv.org/abs/2604.05529