EncounterMob：基于大语言模型的相遇驱动城市级人类移动生成框架
Encounter-Driven City-Scale Human Mobility Generation with Large Language Models
AI 导读
研究者提出 EncounterMob，一个相遇驱动的大语言框架，可同时保留个体移动模式与人群层面的相遇交互结构。框架包含从粗到细的 Encounter Generator 和迭代耦合机制，并引入覆盖相遇边缘与联合分布的评估协议。在日本和 NYC 数据集上，它优于全部基线：相比 ELLMob，将参与者-时间-地点联合误差降低 40.4%/41.7%，个体移动平均误差降低 58.8%/32.7%。
正文 · 原文
Abstract:Large language models (LLMs) have shown strong potential for human mobility generation by modeling individual routines, activities, and mobility preferences. However, existing approaches remain largely resident-centric: generating realistic individual trajectories does not necessarily recover the encounters that emerge when multiple residents co-occur at the same place and time. To this end, we study encounter-aware human mobility generation, which jointly preserves individual mobility and population-level interaction structure. We propose EncounterMob, an encounter-driven LLM framework consisting of a coarse-to-fine Encounter Generator and an Iterative Coupling Framework. The Encounter Generator first captures city-level encounter rhythms and then instantiates participant-time-venue encounters, while the Iterative Coupling Framework coordinates these encounters with personal mobility behavior through successive refinement. We further introduce an encounter recovery protocol covering encounter marginal and joint distributions over residents, times, and venues. Experiments on the Japan and NYC datasets show that EncounterMob outperforms all external baselines on all seven encounter metrics and all six personal mobility metrics. Compared with ELLMob, it reduces the participant-time-venue joint error by 40.4%/41.7% and the mean personal mobility error by 58.8%/32.7% on Japan/NYC, respectively.
| Comments: | 29 pages, including references and appendices |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17672 [cs.AI] |
| (or arXiv:2610.17672v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17672 arXiv-issued DOI via DataCite |
Submission history
From: Chao Li [view email]
[v1]
Tue, 13 Oct 2026 03:58:00 UTC (18,794 KB)
[v2]
Wed, 28 Oct 2026 02:22:14 UTC (18,794 KB)
来源：arXiv cs.AI · arxiv.org