Towards Efficient and Evidence-grounded Mobility Prediction with LLM-Driven Agent
2026-06-03 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors introduce AgentMob, a new method that predicts where a person will go next without needing extra training. Instead of making a single guess, it first uses simple past patterns to decide quickly. If the situation is unclear, it asks more questions and checks different types of information before choosing, making its predictions clearer and often better. They tested this on three datasets and showed it works well compared to similar methods that don’t use training.
mobility predictionlarge language models (LLM)adaptive decision makingnext-location predictionevidence gatheringsequence modelstransportation planningurban simulationiterative inferencetraining-free methods
Authors
Linyao Chen, Qinlao Zhao, Zechen Li, Mingming Li, Likun Ni, Jinyu Chen, Yuhao Yao, Xuan Song, Noboru Koshizuka, Hiroki Kobayashi
Abstract
Individual-level mobility prediction is central to urban simulation, transportation planning, and policy analysis. Supervised sequence models achieve strong accuracy but require task-specific training and offer limited decision-level transparency. Recent LLM-based methods improve interpretability, yet mostly rely on static prompts and single-pass inference, limiting their ability to seek additional evidence when mobility signals are weak or conflicting. We propose \method{}, a training-free LLM-driven agent framework that formulates next-location prediction as adaptive evidence-controlled decision making. \method{} resolves routine cases through a fast path based on historical regularity, while ambiguous cases trigger iterative tool use over recent trajectories, historical behavior, stay-move likelihood, and geographical evidence. Across three mobility datasets, AgentMob achieves the strongest overall performance among training-free LLM-based methods, with GPT-5.4 reaching 71.42\% Acc@1 on BW, 33.14\% on YJMob100K, and 33.50\% on Shanghai ISP. On BW non-fast-path cases, the LLM controller improves Acc@1 from 30.65\% to 48.62\% over a same-tool statistical baseline, showing that its main benefit lies in resolving ambiguous predictions through adaptive evidence gathering. Our code is available at https://github.com/Unknown-zoo/AgentMob.