• M2LSimu introduces a mobility-measures guided framework for LLM-based human mobility simulation. • It coordinates individual agents using shared data, capturing emergent collective behaviors. • Coarse-grained adjustments refine prompts, then fine-grained adaptation meets population-level objectives. • Limited budget constraints are respected while optimizing multiple mobility metrics. • Experiments on two public datasets show significant performance gains over state-of-the-art. • The approach bridges multi-agent systems and large language models for realistic trajectory generation.
Article Summaries:
- Computer Science > Multiagent Systems [Submitted on 17 Feb 2026] Title:Guiding LLM-Based Human Mobility Simulation with Mobility Measures from Shared Data View PDF HTML (experimental)Abstract:Large-scale human mobility simulation is critical for many science domains such as urban science, epidemiology, and transportation analysis. Recent works treat large language models (LLMs) as human agents to simulate realistic mobility trajectories by modeling individual-level cognitive processes. However, these approaches generate individual mobility trajectories independently, without any population-lev
Sources: