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

arXiv: https://arxiv.org/abs/2607.26724 · HTML: https://mlsanity.com/paper/2607.26724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 15 of 15)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [DABstep: Data Agent Benchmark for Multi-step Reasoning](https://mlsanity.com/paper/2506.23719/) (2025)
- [LAMBDA: A Large Model Based Data Agent](https://mlsanity.com/paper/2407.17535/) (2024)
- [CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks](https://mlsanity.com/paper/2406.13945/) (2024)
- [Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusion](https://mlsanity.com/paper/2309.10547/) (2023)
- [LLM4DS: Evaluating Large Language Models for Data Science Code Generation](https://mlsanity.com/paper/2411.11908/) (2024)
- [CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?](https://mlsanity.com/paper/2606.15300/) (2026)
- [AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research](https://mlsanity.com/paper/2512.07849/) (2025)
- [CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting](https://mlsanity.com/paper/2606.05413/) (2026)

## Abstract (arXiv)

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.