DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle

• URL: http://arxiv.org/abs/2512.04324v1
• Date: Wed, 03 Dec 2025 23:21:28 GMT
• Title: DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
• Authors: Fangyu Lei, Jinxiang Meng, Yiming Huang, Junjie Zhao, Yitong Zhang, Jianwen Luo, Xin Zou, Ruiyi Yang, Wenbo Shi, Yan Gao, Shizhu He, Zuo Wang, Qian Liu, Yang Wang, Ke Wang, Jun Zhao, Kang Liu,
• Abstract summary: Real-world enterprise data intelligence encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights.<n>We introduce DAComp, a benchmark of 210 tasks that mirrors these complex capabilities.
• Score: 41.576417987200074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into decision-oriented insights. We introduce DAComp, a benchmark of 210 tasks that mirrors these complex workflows. Data engineering (DE) tasks require repository-level engineering on industrial schemas, including designing and building multi-stage SQL pipelines from scratch and evolving existing systems under evolving requirements. Data analysis (DA) tasks pose open-ended business problems that demand strategic planning, exploratory analysis through iterative coding, interpretation of intermediate results, and the synthesis of actionable recommendations. Engineering tasks are scored through execution-based, multi-metric evaluation. Open-ended tasks are assessed by a reliable, experimentally validated LLM-judge, which is guided by hierarchical, meticulously crafted rubrics. Our experiments reveal that even state-of-the-art agents falter on DAComp. Performance on DE tasks is particularly low, with success rates under 20%, exposing a critical bottleneck in holistic pipeline orchestration, not merely code generation. Scores on DA tasks also average below 40%, highlighting profound deficiencies in open-ended reasoning and demonstrating that engineering and analysis are distinct capabilities. By clearly diagnosing these limitations, DAComp provides a rigorous and realistic testbed to drive the development of truly capable autonomous data agents for enterprise settings. Our data and code are available at https://da-comp.github.io

Related papers

• DataCross: A Unified Benchmark and Agent Framework for Cross-Modal Heterogeneous Data Analysis [8.171937411588015]
  We introduce DataCross, a novel benchmark and collaborative agent framework for unified, insight-driven analysis.<n>DataCrossBench comprises 200 end-to-end analysis tasks across finance, healthcare, and other domains.<n>We also propose the DataCrossAgent framework, inspired by the "divide-and-synthesis" workflow of human analysts.
  arXiv  Detail & Related papers  (2026-01-29T08:40:45Z)
• Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs [66.63911043019294]
  Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them.<n>This paper focuses on the use of LLM techniques to prepare data for diverse downstream tasks.<n>We introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning, standardization, error processing, imputation, data integration, and data enrichment.
  arXiv  Detail & Related papers  (2026-01-22T12:02:45Z)
• CoDA: Agentic Systems for Collaborative Data Visualization [57.270599188947294]
  Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations.<n>Existing approaches, including simple single- or multi-agent systems, often oversimplify the task.<n>We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection.
  arXiv  Detail & Related papers  (2025-10-03T17:30:16Z)
• Data Agent: A Holistic Architecture for Orchestrating Data+AI Ecosystems [8.816332263275305]
  Traditional Data+AI systems rely heavily on human experts to orchestrate system pipelines.<n>Existing Data+AI systems have limited capabilities in semantic understanding, reasoning, and planning.<n>We propose the concept of a 'Data Agent' - a comprehensive architecture designed to orchestrate Data+AI ecosystems.
  arXiv  Detail & Related papers  (2025-07-02T11:04:49Z)
• DABstep: Data Agent Benchmark for Multi-step Reasoning [2.6709582216950767]
  DABstep is a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks.<n>It comprises over 450 real-world challenges derived from a financial analytics platform.<n>Dabstep is released with a public leaderboard and toolkit to accelerate research in autonomous data analysis.
  arXiv  Detail & Related papers  (2025-06-30T10:49:21Z)
• MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark [51.30875219634243]
  We introduce MMTU, a large-scale benchmark with over 30K questions across 25 real-world table tasks.<n> MMTU is designed to comprehensively evaluate models ability to understand, reason, and manipulate real tables at the expert-level.<n>We show that MMTU require a combination of skills -- including table understanding, reasoning, and coding -- that remain challenging for today's frontier models.
  arXiv  Detail & Related papers  (2025-06-05T21:05:03Z)
• DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation [10.390461679868197]
  We introduce DatawiseAgent, a notebook-centric large language model (LLM) agent framework for adaptive and robust data science automation.<n>Inspired by how human data scientists work in computational notebooks, DatawiseAgent introduces a unified interaction representation and a multi-stage architecture.
  arXiv  Detail & Related papers  (2025-03-10T08:32:33Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• CMDBench: A Benchmark for Coarse-to-fine Multimodal Data Discovery in Compound AI Systems [10.71630696651595]
  Compound AI systems (CASs) that employ LLMs as agents to accomplish knowledge-intensive tasks have garnered significant interest within database and AI communities. silos of multimodal data sources make it difficult to identify appropriate data sources for accomplishing the task at hand. We propose CMDBench, a benchmark modeling the complexity of enterprise data platforms.
  arXiv  Detail & Related papers  (2024-06-02T01:10:41Z)
• DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation [83.30006900263744]
  Data analysis is a crucial analytical process to generate in-depth studies and conclusive insights. We propose to automatically generate high-quality answer annotations leveraging the code-generation capabilities of LLMs. Our DACO-RL algorithm is evaluated by human annotators to produce more helpful answers than SFT model in 57.72% cases.
  arXiv  Detail & Related papers  (2024-03-04T22:47:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.