A Survey of Deep Learning for Geometry Problem Solving

TL;DR

This survey reviews how deep learning techniques are applied to geometry problem solving, covering tasks, methods, evaluation, challenges, and future directions to advance AI's mathematical reasoning capabilities.

Contribution

It provides a comprehensive overview of deep learning applications in geometry problem solving, including tasks, methods, evaluation metrics, and future research directions.

Findings

Summarizes key deep learning methods used in geometry problem solving.

Analyzes evaluation metrics and challenges in the field.

Provides a curated list of relevant papers for ongoing research.

Abstract

Geometry problem solving, a crucial aspect of mathematical reasoning, is vital across various domains, including education, the assessment of AI's mathematical abilities, and multimodal capability evaluation. The recent surge in deep learning technologies, particularly the emergence of multimodal large language models, has significantly accelerated research in this area. This paper provides a survey of the applications of deep learning in geometry problem solving, including (i) a comprehensive summary of the relevant tasks in geometry problem solving; (ii) a thorough review of related deep learning methods; (iii) a detailed analysis of evaluation metrics and methods; and (iv) a critical discussion of the current challenges and future directions that can be explored. Our objective is to offer a comprehensive and practical reference of deep learning for geometry problem solving, thereby fostering further advancements in this field. We create a continuously updated list of papers on GitHub: https://github.com/majianz/dl4gps.