# Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards

arXiv: https://arxiv.org/abs/2603.06958 · HTML: https://mlsanity.com/paper/2603.06958/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL](https://mlsanity.com/paper/2503.07536/) (2025)
- [R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model](https://mlsanity.com/paper/2503.05132/) (2025)
- [DePlot: One-shot visual language reasoning by plot-to-table translation](https://mlsanity.com/paper/2212.10505/) (2022)
- [UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoning](https://mlsanity.com/paper/2305.14761/) (2023)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering](https://mlsanity.com/paper/2405.07001/) (2024)
- [Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning](https://mlsanity.com/paper/2312.10160/) (2023)
- [EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding](https://mlsanity.com/paper/2409.01577/) (2024)
- [MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems](https://mlsanity.com/paper/2410.14179/) (2024)
- [Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models](https://mlsanity.com/paper/2502.15678/) (2025)

## Built on by (most cited first, 3 of 3)

- [Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR](https://mlsanity.com/paper/2605.30912/) (2026)
- [When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering](https://mlsanity.com/paper/2608.05670/) (2026)
- [LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification](https://mlsanity.com/paper/2610.01800/) (2026)

## Abstract (arXiv)

Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations. However, existing vision-language models (VLMs) frequently struggle to generalize on unseen charts because it requires abstract, symbolic, and quantitative reasoning over structured visual representations. In this work, we introduce Chart-RL, an effective reinforcement learning (RL) method that employs mathematically verifiable rewards to enhance chart question answering in VLMs. Our experiments demonstrate that Chart-RL consistently outperforms supervised fine-tuning (SFT) across different chart understanding benchmarks, achieving relative improvements of 16.7% on MutlChartQA, and 11.5% on ChartInsights. We conduct robustness analysis, where Chart-RL achieves enhanced performance in 18 of 25 perturbed chart categories, demonstrating strong consistency and reasoning capability across visual variations. Furthermore, we demonstrate that task difficulty and inherent complexity are more critical than data quantity in RL training. For instance, Chart-RL trained on merely 10 complex chart-query examples significantly outperforms models trained on over 6,000 simple examples. Additionally, training on challenging reasoning tasks not only improves in-domain generalization relative to simpler tasks, but also facilitate strong transfer to out-of-domain visual mathematical problems.