# Mario: Multimodal Graph Reasoning with Large Language Models

arXiv: https://arxiv.org/abs/2603.05181 · HTML: https://mlsanity.com/paper/2603.05181/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [GraphGPT: Graph Instruction Tuning for Large Language Models](https://mlsanity.com/paper/2310.13023/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [LLaGA: Large Language and Graph Assistant](https://mlsanity.com/paper/2402.08170/) (2024)
- [GraphText: Graph Reasoning in Text Space](https://mlsanity.com/paper/2310.01089/) (2023)
- [Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?](https://mlsanity.com/paper/2309.16595/) (2023)
- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [Multimodal Graph Learning for Generative Tasks](https://mlsanity.com/paper/2310.07478/) (2023)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Design](https://mlsanity.com/paper/2501.15755/) (2025)
- [Aligning Vision to Language: Annotation-Free Multimodal Knowledge Graph Construction for Enhanced LLMs Reasoning](https://mlsanity.com/paper/2503.12972/) (2025)
- [Graph Neural Networks Exponentially Lose Expressive Power for Node Classification](https://mlsanity.com/paper/1905.10947/) (2019)
- [MLaGA: Multimodal Large Language and Graph Assistant](https://mlsanity.com/paper/2506.02568/) (2025)
- [Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning](https://mlsanity.com/paper/2506.10282/) (2025)
- [ELMM: Efficient Lightweight Multimodal Large Language Models for Multimodal Knowledge Graph Completion](https://mlsanity.com/paper/2510.16753/) (2025)

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

- [GraphVerse: A Comprehensive Visual Graph Reasoning Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2608.06769/) (2026)
- [Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework](https://mlsanity.com/paper/2607.15687/) (2026)
- [Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach](https://mlsanity.com/paper/2610.02881/) (2026)

## Abstract (arXiv)

Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario.