Saved in:
Bibliographic Details
Main Authors: Bai, Yuhang, Ding, Yujuan, Lin, Shanru, Fan, Wenqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18731
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914341963431936
author Bai, Yuhang
Ding, Yujuan
Lin, Shanru
Fan, Wenqi
author_facet Bai, Yuhang
Ding, Yujuan
Lin, Shanru
Fan, Wenqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_18731
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization
Bai, Yuhang
Ding, Yujuan
Lin, Shanru
Fan, Wenqi
Artificial Intelligence
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.
title Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization
topic Artificial Intelligence
url https://arxiv.org/abs/2602.18731