发表机构
Tsinghua University; Jiangmen Municipal Smart Social Governance Technology Innovation Center（清华大学; 江门市智慧社会治理技术创新中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对数据密集型城市任务中现有LLM智能体依赖有限数据集的问题，提出图引导多智能体系统UrbanDS，构建基准UrbanDS-Bench验证其性能，该系统已在武汉东西湖城市平台落地应用。
AI 中文摘要
大语言模型（LLM）智能体已被广泛应用于自动化数据科学任务。然而，现有方法通常依赖有限的提供数据集，在数据密集型场景中面临挑战，这类场景需要从大规模异构数据仓库中发现并利用相关信息。城市任务是这类场景的典型代表，因为城市数据不仅规模庞大、来源多样，还呈现出复杂的空间、时间和语义关系。为应对这些挑战，我们提出UrbanDS，一种用于数据密集型城市任务的图引导大语言模型多智能体系统。我们首先构建统一数据集图，以组织可复用的数据集技能及数据集间的关系。具体而言，我们开发了数据画像智能体（Data Profiling Agent），为每个数据集构建一项技能；此外，关系智能体（Relation Agent）识别数据集间的关系，并将这些关系整合到数据集图中。在运行时，规划智能体（Planner Agent）从图中检索任务相关数据集并生成执行计划；多个执行智能体（Execution Agents）随后执行数据处理与分析，其执行进度和中间结果通过公共内存共享；最后，报告智能体（Report Agent）将实验日志合成为报告，该报告可根据用户反馈进一步优化。为系统评估智能体处理数据密集型城市场景的能力，我们还构建了UrbanDS-Bench，一个涵盖代表性数据分析与建模任务的城市数据科学基准。在通用基准和城市基准上的实验表明，UrbanDS在数据密集型任务上始终优于现有数据科学智能体。此外，UrbanDS已部署于武汉市东西湖区的城市运营平台，展现出其在实际城市应用中的有效性。
英文摘要
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.
