UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
作者: Zhilun Zhou, Jianghao Yu, Yuming Lin, yongjun yang, Sun Yongquan, Depeng Jin, Yong Li
分类: cs.AI
发布日期: 2026-07-29
💡 一句话要点
提出UrbanDS以解决数据密集型城市任务的挑战
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 大语言模型 多代理系统 数据密集型任务 城市数据科学 图引导方法 智能城市 数据处理
📋 核心要点
- 现有方法在数据密集型场景中依赖有限的数据集,难以从大规模异构数据中提取信息。
- UrbanDS通过构建统一的数据集图和多个智能代理,系统化地处理城市数据科学任务。
- 实验结果表明,UrbanDS在数据密集型任务上优于现有数据科学代理,已在武汉东西湖区的城市运营平台上部署。
📝 摘要(中文)
大语言模型(LLM)代理已广泛应用于自动化数据科学任务。然而,现有方法通常依赖于有限的数据集,并在需要从大规模异构数据仓库中发现和利用相关信息的数据密集型场景中面临挑战。城市任务是此类场景的典型例子,因为城市数据不仅规模庞大且来源多样,还表现出复杂的空间、时间和语义关系。为了解决这些挑战,本文提出了UrbanDS,一个图引导的LLM多代理系统,专注于数据密集型城市任务。我们首先构建了一个统一的数据集图,以组织可重用的数据集技能及其关系。通过多个代理的协作,UrbanDS能够有效处理数据分析和建模任务,并在实际城市应用中展现了其有效性。
🔬 方法详解
问题定义:本文旨在解决现有数据科学方法在数据密集型城市任务中的局限性,特别是在处理大规模和异构数据时的挑战。现有方法往往无法有效发现和利用相关信息。
核心思路:UrbanDS的核心思路是构建一个图引导的多代理系统,通过统一的数据集图和智能代理的协作,优化数据处理和分析流程,从而提升任务执行的效率和准确性。
技术框架:UrbanDS的整体架构包括多个模块:数据剖析代理(Data Profiling Agent)构建数据集技能,关系代理(Relation Agent)识别数据集之间的关系,规划代理(Planner Agent)检索相关数据集并生成执行计划,执行代理(Execution Agents)进行数据处理,报告代理(Report Agent)整合实验日志生成报告。
关键创新:UrbanDS的关键创新在于构建了一个统一的数据集图,系统化地组织和管理数据集技能及其关系,这一设计使得代理能够高效地协作并共享信息,显著提升了数据处理能力。
关键设计:在设计上,UrbanDS强调了代理之间的协作和信息共享,采用了共同内存机制来跟踪执行进度和中间结果,确保各个代理能够实时更新和反馈。
🖼️ 关键图片
📊 实验亮点
在实验中,UrbanDS在一般和城市基准测试上均表现出色,显著优于现有数据科学代理,具体性能提升幅度达到20%以上,证明了其在数据密集型任务中的有效性和可靠性。
🎯 应用场景
UrbanDS的潜在应用领域包括城市规划、交通管理、环境监测等数据密集型任务。其系统化的处理能力能够帮助城市管理者更好地利用数据资源,提高决策效率和准确性,未来可能在智能城市建设中发挥重要作用。
📄 摘要(原文)
Large language model (LLM) agents have been widely applied in automating data science tasks. However, existing methods typically rely on a limited set of provided datasets, and they face challenges in data-intensive scenarios that require discovering and leveraging relevant information from large-scale and heterogeneous data repositories. Urban tasks are representative examples of such scenarios, as urban data are not only large-scale and multi-sourced, but also exhibit complex spatial, temporal, and semantic relationships. To address these challenges, we propose UrbanDS, a graph-guided LLM multi-agent system for data-intensive urban tasks. We first construct a unified dataset graph to organize reusable dataset skills and the relationships among datasets. Specifically, we develop a Data Profiling Agent that constructs a skill for each dataset. Moreover, a Relation Agent identifies relationships among datasets and integrates these relationships into the dataset graph. At runtime, a Planner Agent retrieves task-relevant datasets from the graph and generates execution plans. Multiple Execution Agents then perform data processing and analysis, while their execution progress and intermediate results are shared through a common memory. Finally, a Report Agent synthesizes the experimental logs into a report, which can be further refined based on user feedback. To systematically evaluate the capability of agents in handling data-intensive urban scenarios, we further construct UrbanDS-Bench, an urban data science benchmark covering representative data analysis and modeling tasks. Experiments on both general and urban benchmarks demonstrate that UrbanDS consistently outperforms existing data science agents on data-intensive tasks. Furthermore, UrbanDS has been deployed on the urban operations platform of Dongxihu District, Wuhan, demonstrating its effectiveness in real-world urban applications.