A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning

TL;DR

This survey reviews recent advances in Multimodal Mathematical Reasoning, highlighting challenges in perception, alignment, and reasoning, and discusses evaluation methods and future research directions.

Contribution

It systematically categorizes MMR approaches around key questions, providing a comprehensive roadmap for understanding and comparing existing methods.

Findings

Current models struggle with diagram interpretation and symbol alignment.

Existing evaluations focus mainly on final answers rather than reasoning steps.

Recent research integrates perception, alignment, and reasoning for improved performance.

Abstract

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.