Saved in:
Bibliographic Details
Main Authors: Yang, Tianyu, Wu, Sihong, Zhao, Yilun, Liang, Zhenwen, Dai, Lisen, Zhao, Chen, Cheng, Minhao, Cohan, Arman, Zhang, Xiangliang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.08291
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915936973357056
author Yang, Tianyu
Wu, Sihong
Zhao, Yilun
Liang, Zhenwen
Dai, Lisen
Zhao, Chen
Cheng, Minhao
Cohan, Arman
Zhang, Xiangliang
author_facet Yang, Tianyu
Wu, Sihong
Zhao, Yilun
Liang, Zhenwen
Dai, Lisen
Zhao, Chen
Cheng, Minhao
Cohan, Arman
Zhang, Xiangliang
contents Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both textual and visual modalities. However, current models still face significant challenges in real-world visual math tasks, often misinterpreting diagrams, failing to align mathematical symbols with visual evidence, or producing inconsistent reasoning steps. Moreover, existing evaluations mainly focus on checking final answers rather than verifying the correctness or executability of each intermediate step. A growing body of recent research addresses these issues by integrating structured perception, explicit alignment, and verifiable reasoning within unified frameworks. To establish a clear roadmap for understanding and comparing different MMR approaches, we systematically review them around four fundamental questions: (1) What to extract from multimodal inputs, (2) How to represent and align textual and visual information, (3) How to perform the reasoning, and (4) How to evaluate the correctness of the overall reasoning process. Finally, we discuss open challenges and share our thoughts on future research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08291
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning
Yang, Tianyu
Wu, Sihong
Zhao, Yilun
Liang, Zhenwen
Dai, Lisen
Zhao, Chen
Cheng, Minhao
Cohan, Arman
Zhang, Xiangliang
Artificial Intelligence
Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems involving both textual and visual modalities. However, current models still face significant challenges in real-world visual math tasks, often misinterpreting diagrams, failing to align mathematical symbols with visual evidence, or producing inconsistent reasoning steps. Moreover, existing evaluations mainly focus on checking final answers rather than verifying the correctness or executability of each intermediate step. A growing body of recent research addresses these issues by integrating structured perception, explicit alignment, and verifiable reasoning within unified frameworks. To establish a clear roadmap for understanding and comparing different MMR approaches, we systematically review them around four fundamental questions: (1) What to extract from multimodal inputs, (2) How to represent and align textual and visual information, (3) How to perform the reasoning, and (4) How to evaluate the correctness of the overall reasoning process. Finally, we discuss open challenges and share our thoughts on future research directions.
title A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2603.08291