Reproduce “AgenticMobility: An Open-Source Platform for Multi-AI-Agent Mobility Dynamics” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Jiaheng Xiao, Jiangtao Han, Jiachen Wang, Honghai Li, Lijun Sun, Kay Axhausen, Chang Liu, Zhengbing He

AgenticMobility links persistent travelers and managers through bounded decisions, execution in MATSim, and feedback across repeated days. In one 100-day run per configuration, the combined configuration had lower mean target-trip car time than LLM Traveler alone (16.25 versus 17.40 minutes), but higher daily car time per simulated person (40.71 versus 35.52 minutes). This contrast is illustrative, not causal evidence.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.