# When Vision Meets Graphs: A Survey on Graph Reasoning and Learning

arXiv: https://arxiv.org/abs/2609.03816 · HTML: https://mlsanity.com/paper/2609.03816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 22 of its 64 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 22 of 22)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens](https://mlsanity.com/paper/2511.19418/) (2025)
- [GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability](https://mlsanity.com/paper/2403.04483/) (2024)
- [Spectral Augmentation for Self-Supervised Learning on Graphs](https://mlsanity.com/paper/2210.00643/) (2022)
- [Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models](https://mlsanity.com/paper/1706.06689/) (2017)
- [GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks](https://mlsanity.com/paper/2504.12764/) (2025)
- [GraphBench: Next-generation graph learning benchmarking](https://mlsanity.com/paper/2512.04475/) (2025)
- [TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks](https://mlsanity.com/paper/2511.06283/) (2025)
- [Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners](https://mlsanity.com/paper/2511.10234/) (2025)
- [Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models](https://mlsanity.com/paper/2503.21435/) (2025)
- [MolVision: Molecular Property Prediction with Vision Language Models](https://mlsanity.com/paper/2507.03283/) (2025)
- [The Underappreciated Power of Vision Models for Graph Structural Understanding](https://mlsanity.com/paper/2510.24788/) (2025)
- [VisGraphVar: A Benchmark Generator for Assessing Variability in Graph Analysis Using Large Vision-Language Models](https://mlsanity.com/paper/2411.14832/) (2024)
- [AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research](https://mlsanity.com/paper/2505.12039/) (2025)
- [MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models](https://mlsanity.com/paper/2608.23646/) (2026)
- [Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark](https://mlsanity.com/paper/2405.06634/) (2024)
- [Scope: Selective Cross-modal Orchestration of Visual Perception Experts](https://mlsanity.com/paper/2510.12974/) (2025)
- [See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models](https://mlsanity.com/paper/2510.16769/) (2025)
- [GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2608.06769/) (2026)
- [Rethinking Spectral Augmentation for Contrast-based Graph Self-Supervised Learning](https://mlsanity.com/paper/2405.19600/) (2024)

## Abstract (arXiv)

Graphs are a fundamental data structure underlying many problems in the natural and social sciences. Over the past decade, Graph Neural Networks (GNNs) have dominated graph machine learning, supported by solid theoretical foundations. Yet scientists often understand graph structure through vision: chemists read molecular diagrams and social scientists inspect network visualizations. Despite decades of work on graph visualization, most graph learning pipelines still treat graphs purely as symbolic structures, rarely leveraging the visual form of graphs. We argue that this gap deserves renewed attention in the era of powerful vision and vision-language models. This survey provides a first systematic overview of the emerging area we term vision meets graphs, which treats visual depictions of graphs as first-class inputs for reasoning and learning. We organize existing work into three threads. Vision for Graph Reasoning studies how models can use visual depictions of graphs to understand structure and carry out multi-step reasoning. Vision for Graph Learning explores how visual features can complement or augment graph encoders beyond known limitations of message passing. Scientific Graphs examines domains where standardized depiction conventions support both reasoning and learning. Our goal is to clarify what current methods can and cannot do, and to outline a path toward foundation models that perceive and reason about graphs as scientists do.