DV-World：在真實世界場景中對資料視覺化代理進行基準測試

摘要

現實世界的資料視覺化需要具備原生環境基礎、跨平台演進能力及主動意圖對齊。然而現有基準測試常受限於程式碼沙箱隔離、僅支援單一語言的創作型任務，以及對完美意圖的假設。為彌合這些差距，我們推出DV-World基準測試套件，包含260項任務，旨在全面評估資料視覺化代理在真實專業工作流程中的表現。DV-World涵蓋三大領域：DV-Sheet專注原生試算表操作，包含圖表與儀表板創建及診斷修復；DV-Evolution針對跨程式典範的參考視覺作品改編與重構；DV-Interact則透過模擬真實世界模糊需求的使用者模擬器，實現主動意圖對齊。我們的混合評估框架整合了確保數值精確度的表格值對齊技術，以及採用評分規程進行語義視覺評估的多模態大模型評判機制。實驗顯示，現有頂尖模型的整體表現不足50%，暴露其在處理真實世界資料視覺化複雜挑戰時的關鍵缺陷。DV-World提供了一個貼近現實的測試平台，可引導技術發展朝向企業工作流程所需的多元專業能力邁進。本專案資料與程式碼已公開於：https://github.com/DA-Open/DV-World{專案頁面}。

English

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 https://github.com/DA-Open/DV-World{this project page}.

DV-World：在真實世界場景中對資料視覺化代理進行基準測試

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

摘要

Support