Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

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

Source

arXiv

arxiv.org/abs/2607.26724v1

Read the source

Source

Plain-Language Brief

Researchers have developed a system called UrbanDS that helps automate data science tasks for urban scenarios. UrbanDS is a graph-guided multi-agent system designed to handle large-scale and heterogeneous data repositories, including those found in urban environments. The system consists of several agents: Data Profiling Agent, Relation Agent, Planner Agent, Execution Agents, and Report Agent. These agents work together to construct a unified dataset graph, identify relationships among datasets, generate execution plans, perform data processing and analysis, and synthesize reports based on experimental logs.

What the Document Says

  • The researchers propose UrbanDS, a graph-guided LLM multi-agent system for data-intensive urban tasks.
  • The system constructs a unified dataset graph to organize reusable dataset skills and the relationships among datasets.
  • A Data Profiling Agent is developed to construct a skill for each dataset.
  • 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 perform data processing and analysis.
  • Their execution progress and intermediate results are shared through a common memory.
  • A Report Agent synthesizes the experimental logs into a report.
  • UrbanDS consistently outperforms existing data science agents on data-intensive tasks.
  • UrbanDS has been deployed in the urban operations platform of Dongxihu District, Wuhan.

Key Concepts Mentioned

  • Large language model (LLM) agents
  • data science tasks
  • urban tasks
  • dataset graph
  • Data Profiling Agent
  • Relation Agent
  • Planner Agent
  • Execution Agents
  • Report Agent
  • UrbanDS-Bench

Claims Made by the Document

  • UrbanDS outperforms existing data science agents on data-intensive tasks.
  • UrbanDS has been deployed in real-world urban applications.

Evidence Used

  • The text states that experiments demonstrate UrbanDS outperforms existing data science agents on data-intensive tasks.
  • The text mentions that UrbanDS has been deployed on the urban operations platform of Dongxihu District, Wuhan.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.