Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System

• URL: http://arxiv.org/abs/2511.00096v1
• Date: Thu, 30 Oct 2025 10:26:02 GMT
• Title: Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System
• Authors: Shangyu Lou,
• Abstract summary: Urban Artificial Intelligence (Urban AI) has advanced human-centered urban tasks such as perception prediction and human dynamics.<n>Large Language Models (LLMs) can integrate multimodal inputs to address heterogeneous data in complex urban systems but often underperform on domain-specific tasks.<n>Urban-MAS, an LLM-based Multi-Agent System (MAS), is introduced for human-centered urban prediction under zero-shot settings.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Urban Artificial Intelligence (Urban AI) has advanced human-centered urban tasks such as perception prediction and human dynamics. Large Language Models (LLMs) can integrate multimodal inputs to address heterogeneous data in complex urban systems but often underperform on domain-specific tasks. Urban-MAS, an LLM-based Multi-Agent System (MAS) framework, is introduced for human-centered urban prediction under zero-shot settings. It includes three agent types: Predictive Factor Guidance Agents, which prioritize key predictive factors to guide knowledge extraction and enhance the effectiveness of compressed urban knowledge in LLMs; Reliable UrbanInfo Extraction Agents, which improve robustness by comparing multiple outputs, validating consistency, and re-extracting when conflicts occur; and Multi-UrbanInfo Inference Agents, which integrate extracted multi-source information across dimensions for prediction. Experiments on running-amount prediction and urban perception across Tokyo, Milan, and Seattle demonstrate that Urban-MAS substantially reduces errors compared to single-LLM baselines. Ablation studies indicate that Predictive Factor Guidance Agents are most critical for enhancing predictive performance, positioning Urban-MAS as a scalable paradigm for human-centered urban AI prediction. Code is available on the project website:https://github.com/THETUREHOOHA/UrbanMAS

Related papers

• UrbanMoE: A Sparse Multi-Modal Mixture-of-Experts Framework for Multi-Task Urban Region Profiling [47.568568425459716]
  We develop a benchmark for multi-task urban region profiling, featuring multi-modal features and a diverse set of strong baselines.<n>We then propose UrbanMoE, the first sparse multi-modal, multi-expert framework specifically architected to solve the multi-task challenge.<n>We conduct extensive experiments on three real-world datasets within our benchmark, where UrbanMoE consistently demonstrates superior performance over all baselines.
  arXiv  Detail & Related papers  (2026-01-30T09:25:05Z)
• AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing [31.732273940704843]
  AgentSense is a training-free framework that integrates large language models into participatory urban sensing.<n>We show that AgentSense offers distinct advantages in adaptivity and explainability over traditional methods.
  arXiv  Detail & Related papers  (2025-10-22T15:06:26Z)
• Urban-R1: Reinforced MLLMs Mitigate Geospatial Biases for Urban General Intelligence [64.36291202666212]
  Urban General Intelligence (UGI) refers to AI systems that can understand and reason about complex urban environments.<n>Recent studies have built urban foundation models using supervised fine-tuning (SFT) of LLMs and MLLMs.<n>We propose Urban-R1, a reinforcement learning-based post-training framework that aligns MLLMs with the objectives of UGI.
  arXiv  Detail & Related papers  (2025-10-18T15:59:09Z)
• FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction [92.7392863957204]
  FutureX is the largest and most diverse live benchmark for future prediction.<n>It supports real-time daily updates and eliminates data contamination through an automated pipeline for question gathering and answer collection.<n>We evaluate 25 LLM/agent models, including those with reasoning, search capabilities, and integration of external tools.
  arXiv  Detail & Related papers  (2025-08-16T08:54:08Z)
• Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications [11.994794218481122]
  Large Language Models (LLMs) have opened new ways toward realizing the vision of intelligent cities.<n>In this article, we focus on Urban LLM Agents, which are semi-embodied within the hybrid cyber-physical-social space of cities.
  arXiv  Detail & Related papers  (2025-07-01T16:18:29Z)
• USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents [6.054990893127997]
  Large language models (LLMs) have shown emerging potential intemporal, reasoning making them promising candidates for building urban agents that support diverse urban downstream applications.<n>Existing studies on evaluating urban agents on outcome-level studies offer limited insight into their underlying reasoning processes.<n>As a result, strengths and limitations of urban agents intemporal reasoning remain poorly understood.<n>USTBench is the first benchmark to evaluate LLMs'temporal reasoning abilities as urban agents across four dimensions:temporal understanding, forecasting, planning, and reflection with feedback.
  arXiv  Detail & Related papers  (2025-05-23T07:30:57Z)
• UrbanMind: Urban Dynamics Prediction with Multifaceted Spatial-Temporal Large Language Models [18.051209616917042]
  UrbanMind is a novel spatial-temporal LLM framework for multifaceted urban dynamics prediction.<n>At its core, UrbanMind introduces Muffin-MAE, a multifaceted fusion masked autoencoder with specialized masking strategies.<n>Experiments on real-world urban datasets across multiple cities demonstrate that UrbanMind consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-05-16T19:38:06Z)
• AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction [7.007450097312181]
  We introduce AgentMove, a systematic agentic prediction framework to achieve generalized next location prediction.<n>In AgentMove, we first decompose the mobility prediction task and design specific modules to complete them, including spatial-temporal memory for individual mobility pattern mining.<n>Experiments utilizing mobility data from two distinct sources reveal that AgentMove surpasses the leading baseline by 3.33% to 8.57% across 8 out of 12 metrics.
  arXiv  Detail & Related papers  (2024-08-26T02:36:55Z)
• CityX: Controllable Procedural Content Generation for Unbounded 3D Cities [50.10101235281943]
  Current generative methods fall short in either diversity, controllability, or fidelity.<n>In this work, we resort to the procedural content generation (PCG) technique for high-fidelity generation.<n>We develop a multi-agent framework to transform multi-modal instructions, including OSM, semantic maps, and satellite images, into executable programs.<n>Our method, named CityX, demonstrates its superiority in creating diverse, controllable, and realistic 3D urban scenes.
  arXiv  Detail & Related papers  (2024-07-24T18:05:13Z)
• CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks [10.22654338686634]
  Large language models (LLMs) and vision-language models (VLMs) have become essential to ensure their real-world effectiveness and reliability.<n>The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data.<n>In this paper, we design textitCityBench, an interactive simulator based evaluation platform.
  arXiv  Detail & Related papers  (2024-06-20T02:25:07Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• Model-based Reinforcement Learning for Decentralized Multiagent Rendezvous [66.6895109554163]
  Underlying the human ability to align goals with other agents is their ability to predict the intentions of others and actively update their own plans. We propose hierarchical predictive planning (HPP), a model-based reinforcement learning method for decentralized multiagent rendezvous.
  arXiv  Detail & Related papers  (2020-03-15T19:49:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.