English

CharTool: Tool-Integrated Visual Reasoning for Chart Understanding

Artificial Intelligence 2026-04-06 v1

Abstract

Charts are ubiquitous in scientific and financial literature for presenting structured data. However, chart reasoning remains challenging for multimodal large language models (MLLMs) due to the lack of high-quality training data, as well as the need for fine-grained visual grounding and precise numerical computation. To address these challenges, we first propose DuoChart, a scalable dual-source data pipeline that combines synthesized charts with real-world charts to construct diverse, high-quality chart training data. We then introduce CharTool, which equips MLLMs with external tools, including image cropping for localized visual perception and code-based computation for accurate numerical reasoning. Through agentic reinforcement learning on DuoChart, CharTool learns tool-integrated reasoning grounded in chart content. Extensive experiments on six chart benchmarks show that our method consistently improves over strong MLLM baselines across model scales. Notably, CharTool-7B outperforms the base model by **+8.0%** on CharXiv (Reasoning) and **+9.78%** on ChartQAPro, while achieving competitive performance with substantially larger or proprietary models. Moreover, CharTool demonstrates positive generalization to out-of-domain visual math reasoning benchmarks.

Keywords

Cite

@article{arxiv.2604.02794,
  title  = {CharTool: Tool-Integrated Visual Reasoning for Chart Understanding},
  author = {Situo Zhang and Yifan Zhang and Zichen Zhu and Da Ma and Lei Pan and Danyang Zhang and Zihan Zhao and Lu Chen and Kai Yu},
  journal= {arXiv preprint arXiv:2604.02794},
  year   = {2026}
}
R2 v1 2026-07-01T11:52:28.105Z