arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.04023cs.AIcs.CL
收藏

基于大语言模型的数据科学智能体:能力、挑战与未来方向综述

LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions

York University(约克大学);Vector Institute for AI(人工智能矢量研究所);Dialpad Inc.(Dialpad公司);Nanyang Technological University(南洋理工大学);Salesforce AI Research(Salesforce人工智能研究)

Mizanur Rahman, Amran Bhuiyan, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Ridwan Mahbub, Ahmed Masry, Shafiq Joty, Enamul Hoque

AI总结:

本综述首次提出与数据科学生命周期对齐的分类体系,分析45个LLM驱动的数据科学智能体的阶段分布与设计维度,指出当前研究的侧重偏向与核心挑战,并提出未来发展方向。

摘要:

大语言模型(LLM)的最新进展催生了一类新型AI智能体,这类智能体通过整合规划、工具使用以及跨文本、代码、表格、可视化内容的多模态推理,能够自动化数据科学工作流的多个阶段。本综述首次提出了与数据科学生命周期对齐的综合分类体系,将45个系统系统地分析并映射到端到端数据科学流程的六个阶段:业务理解与数据获取、探索性分析与可视化、特征工程、模型构建与选择、解释与说明、部署与监控。除了生命周期覆盖维度,我们还从五个跨领域设计维度对每个智能体进行标注:推理与规划风格、模态整合方式、工具编排深度、学习与对齐方法,以及信任、安全与治理机制。在分类之外,我们对智能体的能力进行了批判性综合,突出了每个阶段的优势与局限性,并梳理了新兴的基准与评估实践。我们的分析识别出三大关键趋势:大多数系统侧重探索性分析、可视化与建模,却忽视业务理解、部署与监控环节;多模态推理与工具编排仍是未解决的挑战;超过90%的系统缺乏明确的信任与安全机制。最后,我们概述了对齐稳定性、可解释性、治理以及鲁棒评估框架方面的开放性挑战,并提出了未来研究方向,以指导开发鲁棒、可信、低延迟、透明且广泛可及的数据科学智能体。

英文摘要:

Recent advances in large language models (LLMs) have enabled a new class of AI agents that automate multiple stages of the data science workflow by integrating planning, tool use, and multimodal reasoning across text, code, tables, and visuals. This survey presents the first comprehensive, lifecycle-aligned taxonomy of data science agents, systematically analyzing and mapping forty-five systems onto the six stages of the end-to-end data science process: business understanding and data acquisition, exploratory analysis and visualization, feature engineering, model building and selection, interpretation and explanation, and deployment and monitoring. In addition to lifecycle coverage, we annotate each agent along five cross-cutting design dimensions: reasoning and planning style, modality integration, tool orchestration depth, learning and alignment methods, and trust, safety, and governance mechanisms. Beyond classification, we provide a critical synthesis of agent capabilities, highlight strengths and limitations at each stage, and review emerging benchmarks and evaluation practices. Our analysis identifies three key trends: most systems emphasize exploratory analysis, visualization, and modeling while neglecting business understanding, deployment, and monitoring; multimodal reasoning and tool orchestration remain unresolved challenges; and over 90% lack explicit trust and safety mechanisms. We conclude by outlining open challenges in alignment stability, explainability, governance, and robust evaluation frameworks, and propose future research directions to guide the development of robust, trustworthy, low-latency, transparent, and broadly accessible data science agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑