DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Jinxiang, Huang, Shaoping, Lei, Fangyu, Guo, Jingyu, Liu, Haoxiang, Su, Jiahao, Wang, Sihan, Wang, Yao, Wang, Enrui, Yang, Ye, Chai, Hongze, Lv, Jinming, Yu, Anbang, Zhang, Huangjing, Zhang, Yitong, Huang, Yiming, Ma, Zeyao, He, Shizhu, Zhao, Jun, Liu, Kang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914514620907520
author Meng, Jinxiang
Huang, Shaoping
Lei, Fangyu
Guo, Jingyu
Liu, Haoxiang
Su, Jiahao
Wang, Sihan
Wang, Yao
Wang, Enrui
Yang, Ye
Chai, Hongze
Lv, Jinming
Yu, Anbang
Zhang, Huangjing
Zhang, Yitong
Huang, Yiming
Ma, Zeyao
He, Shizhu
Zhao, Jun
Liu, Kang
author_facet Meng, Jinxiang
Huang, Shaoping
Lei, Fangyu
Guo, Jingyu
Liu, Haoxiang
Su, Jiahao
Wang, Sihan
Wang, Yao
Wang, Enrui
Yang, Ye
Chai, Hongze
Lv, Jinming
Yu, Anbang
Zhang, Huangjing
Zhang, Yitong
Huang, Yiming
Ma, Zeyao
He, Shizhu
Zhao, Jun
Liu, Kang
contents Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at \href{https://github.com/DA-Open/DV-World}{this project page}.
format Preprint
id arxiv_https___arxiv_org_abs_2604_25914
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
Meng, Jinxiang
Huang, Shaoping
Lei, Fangyu
Guo, Jingyu
Liu, Haoxiang
Su, Jiahao
Wang, Sihan
Wang, Yao
Wang, Enrui
Yang, Ye
Chai, Hongze
Lv, Jinming
Yu, Anbang
Zhang, Huangjing
Zhang, Yitong
Huang, Yiming
Ma, Zeyao
He, Shizhu
Zhao, Jun
Liu, Kang
Computation and Language
Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from code-sandbox confinement, single-language creation-only tasks, and assumption of perfect intent. To bridge these gaps, we introduce DV-World, a benchmark of 260 tasks designed to evaluate DV agents across real-world professional lifecycles. DV-World spans three domains: DV-Sheet for native spreadsheet manipulation including chart and dashboard creation as well as diagnostic repair; DV-Evolution for adapting and restructuring reference visual artifacts to fit new data across diverse programming paradigms and DV-Interact for proactive intent alignment with a user simulator that mimics real-world ambiguous requirements. Our hybrid evaluation framework integrates Table-value Alignment for numerical precision and MLLM-as-a-Judge with rubrics for semantic-visual assessment. Experiments reveal that state-of-the-art models achieve less than 50% overall performance, exposing critical deficits in handling the complex challenges of real-world data visualization. DV-World provides a realistic testbed to steer development toward the versatile expertise required in enterprise workflows. Our data and code are available at \href{https://github.com/DA-Open/DV-World}{this project page}.
title DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
topic Computation and Language
url https://arxiv.org/abs/2604.25914