AgenticMobility: An Open-Source Platform for Multi-AI-Agent Mobility Dynamics
Abstract
Understanding mobility dynamics and the effects of urban transportation management policies requires examining how individual travel decisions, traffic conditions, and policy interventions influence one another over time. We present AgenticMobility, an open-source experimental platform for studying how mobility AI agents and other AI agents interact, adapt through repeated experience, and collectively shape mobility outcomes. Persistent agents retain identities and relevant states across rounds, with explicit interfaces defining information access, admissible actions, and decision schedules; linked records trace decisions, execution, and feedback. In the current implementation, large language model (LLM) agents act as travelers choosing routes and departure times and as a manager periodically adjusting link charges within MATSim. A preliminary demonstration spans 100 simulated days in each of five configurations, with one run per configuration and a shared simulation seed. In the joint traveler--manager run, all 1,179,300 finalized target decisions satisfied action constraints; execution checks verified implementation of accepted choices and preservation of personal memories across days. Trajectories show stable route choices alongside departure-time adjustments and differences between controlled-trip and population-wide outcomes. The platform supports experiments on individual adaptation, collective outcomes, and management interventions by varying information access, retained experience, and management feedback. Source code is available at https://github.com/Agentic-City-Research/Agentic-Mobility
Related
- Non-negative differential mobility of one-dimensional underdamped Langevin dynamics: Proof via mapping to a marginally stable oscillator
- Mobility-network topology carries incremental, softness-orthogonal information about future aging dynamics in a glass-forming liquid
- Glassy dynamics of metropolitan human mobility frozen near the gravitational equilibrium
- GXNU MolStudio: An Integrated Open-Source Platform for Molecular Visualization and Quantum Chemical Analysis
- Omni-iEEG Planner: an open-source Python platform integrating multimodal neuroimaging and intracranial EEG data for epilepsy surgery research
BibTeX
@misc{xiao2026agenticmobility,
title = {{AgenticMobility: An Open-Source Platform for Multi-AI-Agent Mobility Dynamics}},
author = {Jiaheng Xiao and Jiangtao Han and Jiachen Wang and Honghai Li and Lijun Sun and Kay Axhausen and Chang Liu and Zhengbing He},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01918},
eprint = {2611.01918},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01918},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - AgenticMobility: An Open-Source Platform for Multi-AI-Agent Mobility Dynamics
AU - Jiaheng Xiao
AU - Jiangtao Han
AU - Jiachen Wang
AU - Honghai Li
AU - Lijun Sun
AU - Kay Axhausen
AU - Chang Liu
AU - Zhengbing He
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01918
UR - https://arxiv.org/abs/2611.01918
AB - Understanding mobility dynamics and the effects of urban transportation management policies requires examining how individual travel decisions, traffic conditions, and policy interventions influence one another over time. We present AgenticMobility, an open-source experimental platform for studying how mobility AI agents and other AI agents interact, adapt through repeated experience, and collectively shape mobility outcomes. Persistent agents retain identities and relevant states across rounds, with explicit interfaces defining information access, admissible actions, and decision schedules; linked records trace decisions, execution, and feedback. In the current implementation, large language model (LLM) agents act as travelers choosing routes and departure times and as a manager periodically adjusting link charges within MATSim. A preliminary demonstration spans 100 simulated days in each of five configurations, with one run per configuration and a shared simulation seed. In the joint traveler--manager run, all 1,179,300 finalized target decisions satisfied action constraints; execution checks verified implementation of accepted choices and preservation of personal memories across days. Trajectories show stable route choices alongside departure-time adjustments and differences between controlled-trip and population-wide outcomes. The platform supports experiments on individual adaptation, collective outcomes, and management interventions by varying information access, retained experience, and management feedback. Source code is available at https://github.com/Agentic-City-Research/Agentic-Mobility
ER -