Guiding LLM-Based Human Mobility Simulation with Mobility Measures from Shared Data

2026-02-17

AI Summary

This work addresses the limitation of existing large language model (LLM)-based human mobility simulation methods, which lack mechanisms for modeling collective coordination and thus fail to capture emergent group behaviors. To overcome this, the authors propose the M2LSimu framework, which uniquely integrates group-level mobility metrics—extracted from shared observational data—as guiding signals within a multi-granularity prompting strategy. This approach enables joint modeling of individual cognitive processes and aggregate statistical patterns. Under constrained computational budgets, M2LSimu simultaneously optimizes multiple group-level objectives, significantly outperforming state-of-the-art LLM baselines on two public datasets while enhancing both the individual realism and group-level statistical consistency of the generated trajectories.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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-level coordination mechanism, and thus fail to capture the emergence of collective behaviors. To address this issue, we design M2LSimu, a mobility measures-guided multi-prompt adjustment framework that leverages mobility measures derived from shared data as guidance to refine individual-level prompts for realistic mobility generation. Our framework applies coarse-grained adjustment strategies guided by mobility measures, progressively enabling fine-grained individual-level adaptation while satisfying multiple population-level mobility objectives under a limited budget. Experiments show that M2LSimu significantly outperforms state-of-the-art LLM-based methods on two public datasets.

Problem

• human mobility simulation
• large language models
• collective behavior
• population-level coordination
• mobility measures

Innovation

• LLM-based simulation
• mobility measures
• multi-prompt adjustment
• collective behavior
• human mobility modeling