UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Weng, Han, Liu, Zhou, Song, Yuanfeng, Yin, Xiaoming, Chen, Xing, Zhang, Wentao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911247455223808
author Weng, Han
Liu, Zhou
Song, Yuanfeng
Yin, Xiaoming
Chen, Xing
Zhang, Wentao
author_facet Weng, Han
Liu, Zhou
Song, Yuanfeng
Yin, Xiaoming
Chen, Xing
Zhang, Wentao
contents In the real business world, data is stored in a variety of sources, including structured relational databases, unstructured databases (e.g., NoSQL databases), or even CSV/excel files. The ability to extract reasonable insights across these diverse source is vital for business success. Existing benchmarks, however, are limited in assessing agents' capabilities across these diverse data types. To address this gap, we introduce UniDataBench, a comprehensive benchmark designed to evaluate the performance of data analytics agents in handling diverse data sources. Specifically, UniDataBench is originating from real-life industry analysis report and we then propose a pipeline to remove the privacy and sensitive information. It encompasses a wide array of datasets, including relational databases, CSV files to NoSQL data, reflecting real-world business scenarios, and provides unified framework to assess how effectively agents can explore multiple data formats, extract valuable insights, and generate meaningful summaries and recommendations. Based on UniDataBench, we propose a novel LLM-based agent named ReActInsight, an autonomous agent that performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights. Our benchmark and agent together provide a powerful framework for advancing the capabilities of data analytics agents in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2511_01625
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data
Weng, Han
Liu, Zhou
Song, Yuanfeng
Yin, Xiaoming
Chen, Xing
Zhang, Wentao
Databases
In the real business world, data is stored in a variety of sources, including structured relational databases, unstructured databases (e.g., NoSQL databases), or even CSV/excel files. The ability to extract reasonable insights across these diverse source is vital for business success. Existing benchmarks, however, are limited in assessing agents' capabilities across these diverse data types. To address this gap, we introduce UniDataBench, a comprehensive benchmark designed to evaluate the performance of data analytics agents in handling diverse data sources. Specifically, UniDataBench is originating from real-life industry analysis report and we then propose a pipeline to remove the privacy and sensitive information. It encompasses a wide array of datasets, including relational databases, CSV files to NoSQL data, reflecting real-world business scenarios, and provides unified framework to assess how effectively agents can explore multiple data formats, extract valuable insights, and generate meaningful summaries and recommendations. Based on UniDataBench, we propose a novel LLM-based agent named ReActInsight, an autonomous agent that performs end-to-end analysis over diverse data sources by automatically discovering cross-source linkages, decomposing goals, and generating robust, self-correcting code to extract actionable insights. Our benchmark and agent together provide a powerful framework for advancing the capabilities of data analytics agents in real-world applications.
title UniDataBench: Evaluating Data Analytics Agents Across Structured and Unstructured Data
topic Databases
url https://arxiv.org/abs/2511.01625