UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks

• URL: http://arxiv.org/abs/2607.26724v1
• Date: Wed, 29 Jul 2026 10:14:02 GMT
• Title: UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
• Abstract summary: We propose UrbanDS, a graph-guided LLM multi-agent system for data-intensive urban tasks.<n>We first construct a unified dataset graph to organize reusable dataset skills and the relationships among datasets.<n>At runtime, a Planner Agent retrieves task-relevant datasets from the graph and generates execution plans.<n>Multiple Execution Agents then perform data processing and analysis, while their execution progress and intermediate results are shared through a common memory.
• Score: 15.20059091216674
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs [66.63911043019294]
  Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them.<n>This paper focuses on the use of LLM techniques to prepare data for diverse downstream tasks.<n>We introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning, standardization, error processing, imputation, data integration, and data enrichment.
  arXiv  Detail & Related papers  (2026-01-22T12:02:45Z)
• Harnessing Rich Multi-Modal Data for Spatial-Temporal Homophily-Embedded Graph Learning Across Domains and Localities [2.5065738436850835]
  This research proposes a heterogeneous data pipeline that performs cross-domain data fusion.<n>We aim to address complex urban problems across multiple domains and localities by harnessing the rich information over 50 data sources.
  arXiv  Detail & Related papers  (2025-12-11T23:51:54Z)
• Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents [85.02904078131682]
  We introduce the agent data protocol (ADP), a light-weight representation language that serves as an "interlingua" between agent datasets.<n> ADP is expressive enough to capture a large variety of tasks, including API/tool use, browsing, coding, software engineering, and general agentic.<n>All code and data are released publicly, in the hope that ADP could help lower the barrier to standardized, scalable, and reproducible agent training.
  arXiv  Detail & Related papers  (2025-10-28T17:53:13Z)
• Scaling Generalist Data-Analytic Agents [95.05161133349242]
  DataMind is a scalable data synthesis and agent training recipe designed to build generalist data-analytic agents.<n>DataMind tackles three key challenges in building open-source data-analytic agents.
  arXiv  Detail & Related papers  (2025-09-29T17:23:08Z)
• Autonomous Data Agents: A New Opportunity for Smart Data [50.02229219403014]
  Report argues that DataAgents represent a paradigm shift toward autonomous data-to-knowledge systems.<n>DataAgents transform complex and unstructured data into coherent and actionable knowledge.<n>We first examine why the convergence of agentic AI and data-to-knowledge systems has emerged as a critical trend.
  arXiv  Detail & Related papers  (2025-09-23T06:46:41Z)
• Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics [4.107382739138796]
  Urban visual analytics has become essential for deriving insights into pressing real-world problems.<n>The need to manage diverse datasets, distill intricate, and integrate various analytical methods presents a high barrier to entry.<n>We propose Urbanite, a framework for human-AI collaboration in urban visual analytics.
  arXiv  Detail & Related papers  (2025-08-10T15:44:37Z)
• Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems [8.816332263275305]
  Traditional Data+AI systems rely heavily on human experts to orchestrate system pipelines.<n>Existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning.<n>We propose the concept of a 'Data Agent' - a comprehensive architecture designed to orchestrate Data+AI ecosystems.
  arXiv  Detail & Related papers  (2025-07-02T11:04:49Z)
• Making Sense of Data in the Wild: Data Analysis Automation at Scale [0.1747623282473278]
  We propose a novel approach that combines intelligent agents with retrieval augmented generation to automate data analysis, dataset curation and indexing at scale.<n>We demonstrate that our approach results in more detailed dataset descriptions, higher hit rates and greater diversity in dataset retrieval tasks.
  arXiv  Detail & Related papers  (2025-01-27T10:04:10Z)
• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? [58.330879414174476]
  We introduce DSBench, a benchmark designed to evaluate data science agents with realistic tasks.<n>This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions.<n>Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG)
  arXiv  Detail & Related papers  (2024-09-12T02:08:00Z)
• CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems [10.71630696651595]
  Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks have garnered significant interest within database and AI communities. silos of multimodal data sources make it difficult to identify appropriate data sources for accomplishing the task at hand. We propose CMDBench, a benchmark modeling the complexity of enterprise data platforms.
  arXiv  Detail & Related papers  (2024-06-02T01:10:41Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)

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.