用多智能体框架让AI从图表中挖掘深层洞察，超越简单描述。
Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization
- 设计计划-执行式多智能体系统，结合感知与推理能力。
- 在真实图表数据集上显著提升洞察深度与多样性。
- 适合需要精准数据解读的分析师与研究者使用。
图表总结对提升数据可及性和信息高效消费至关重要。然而，现有方法（包括多模态大语言模型）主要聚焦于低层次的数据描述，难以捕捉数据可视化的核心目标——深层洞察。为此，我们提出 Chart Insight Agent Flow，一种基于计划-执行的多智能体框架，有效利用多模态大模型的感知与推理能力，直接从图表图像中挖掘深刻见解。此外，为解决基准缺失问题，我们构建了 ChartSummInsights，一个包含多样真实图表及其由人类数据分析专家撰写的高质量、有洞察力摘要的新数据集。实验结果表明，该方法显著提升了多模态大模型在图表总结任务上的表现，生成的摘要具备更深入且丰富的洞察。
原文摘要 · Abstract (English)
Chart summarization is crucial for enhancing data accessibility and the efficient consumption of information. However, existing methods, including those with Multimodal Large Language Models (MLLMs), primarily focus on low-level data descriptions and often fail to capture the deeper insights which are the fundamental purpose of data visualization. To address this challenge, we propose Chart Insight Agent Flow, a plan-and-execute multi-agent framework effectively leveraging the perceptual and reasoning capabilities of MLLMs to uncover profound insights directly from chart images. Furthermore, to overcome the lack of suitable benchmarks, we introduce ChartSummInsights, a new dataset featuring a diverse collection of real-world charts paired with high-quality, insightful summaries authored by human data analysis experts. Experimental results demonstrate that our method significantly improves the performance of MLLMs on the chart summarization task, producing summaries with deep and diverse insights.
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。