nvAgent用协作智能体实现自然语言转可视化，复杂查询更准确
nvAgent: Automated Data Visualization from Natural Language via Collaborative Agent Workflow
- 三个智能体分工：处理、规划、验证，协同生成图表
- 多表查询准确率提升9.23%，单表提升7.88%
- 适合数据分析师、非技术用户快速生成高质量图表
自然语言到可视化（NL2Vis）旨在将自然语言描述转化为表格数据的视觉呈现，帮助用户从大规模数据中获取洞察。近年来大语言模型在自动生成代码以转换表格数据为可视化方面展现出潜力，但对需跨多表推理的复杂查询仍表现不佳。为此，我们提出一种协作式智能体工作流nvAgent，包含三个智能体：处理器负责数据库处理与上下文过滤，作曲者负责可视化生成规划，验证者负责代码转换与输出验证。在新提出的VisEval基准上的全面评估表明，nvAgent持续优于现有最先进方法，在单表场景下提升7.88%，多表场景下提升9.23%。定性分析进一步显示，nvAgent相较以往模型保持近20%的性能优势，展现出从复杂异构数据源生成高质量可视化表示的能力。
原文摘要 · Abstract (English)
Natural Language to Visualization (NL2Vis) seeks to convert natural-language descriptions into visual representations of given tables, empowering users to derive insights from large-scale data. Recent advancements in Large Language Models (LLMs) show promise in automating code generation to transform tabular data into accessible visualizations. However, they often struggle with complex queries that require reasoning across multiple tables. To address this limitation, we propose a collaborative agent workflow, termed nvAgent, for NL2Vis. Specifically, nvAgent comprises three agents: a processor agent for database processing and context filtering, a composer agent for planning visualization generation, and a validator agent for code translation and output verification. Comprehensive evaluations on the new VisEval benchmark demonstrate that nvAgent consistently surpasses state-of-the-art baselines, achieving a 7.88% improvement in single-table and a 9.23% improvement in multi-table scenarios. Qualitative analyses further highlight that nvAgent maintains nearly a 20% performance margin over previous models, underscoring its capacity to produce high-quality visual representations from complex, heterogeneous data sources.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。