Towards Geometry Problem Solving in the Large Model Era: A Survey
It addresses the fragmented state of GPS research for applications in education and design, though it is incremental as a survey.
This survey synthesizes advancements in geometry problem solving (GPS) by analyzing benchmark construction, parsing methods, and reasoning paradigms, while proposing a unified analytical framework and identifying opportunities for achieving human-level geometric reasoning.
Geometry problem solving (GPS) represents a critical frontier in artificial intelligence, with profound applications in education, computer-aided design, and computational graphics. Despite its significance, automating GPS remains challenging due to the dual demands of spatial understanding and rigorous logical reasoning. Recent advances in large models have enabled notable breakthroughs, particularly for SAT-level problems, yet the field remains fragmented across methodologies, benchmarks, and evaluation frameworks. This survey systematically synthesizes GPS advancements through three core dimensions: (1) benchmark construction, (2) textual and diagrammatic parsing, and (3) reasoning paradigms. We further propose a unified analytical paradigm, assess current limitations, and identify emerging opportunities to guide future research toward human-level geometric reasoning, including automated benchmark generation and interpretable neuro-symbolic integration.