Search papers, labs, and topics across Lattice.
This paper introduces a novel framework that enhances Large Language Models (LLMs) for simulating human spatiotemporal behavior by integrating chain-of-thought (CoT) reasoning with a Model Context Protocol (MCP). The framework employs a five-stage cognitive reasoning process and six MCP tool categories to address limitations in spatial cognition, physical constraint understanding, and group homogenization. Experiments in Shanghai's Lujiazui district demonstrate the framework's effectiveness in generating realistic spatiotemporal activity patterns, achieving high similarity with real mobile signaling data and significant efficiency improvements through parallel processing.
LLMs can now generate realistic human mobility patterns for urban simulations, thanks to a new framework that injects spatial and temporal reasoning skills.
Human spatiotemporal behavior simulation is critical for urban planning research, yet traditional rule-based and statistical approaches suffer from high computational costs, limited generalizability, and poor scalability. While large language models (LLMs) show promise as"world simulators,"they face challenges in spatiotemporal reasoning including limited spatial cognition, lack of physical constraint understanding, and group homogenization tendencies. This paper introduces a framework integrating chain-of-thought (CoT) reasoning with Model Context Protocol (MCP) to enhance LLMs' capability in simulating spatiotemporal behaviors that correspond with validation data patterns. The methodology combines human-like progressive reasoning through a five-stage cognitive framework with comprehensive data processing via six specialized MCP tool categories: temporal management, spatial navigation, environmental perception, personal memory, social collaboration, and experience evaluation. Experiments in Shanghai's Lujiazui district validate the framework's effectiveness across 1,000 generated samples. Results demonstrate high similarity with real mobile signaling data, achieving generation quality scores of 7.86 to 8.36 across different base models. Parallel processing experiments show efficiency improvements, with generation times decreasing from 1.30 to 0.17 minutes per sample when scaling from 2 to 12 processes. This work contributes to integrating CoT reasoning with MCP for urban behavior modeling, advancing LLMs applications in urban computing and providing a practical approach for synthetic mobility data generation. The framework offers a foundation for smart city planning, transportation forecasting, and participatory urban design applications.
