Towards Geometry Problem Solving in the Large Model Era: A Survey
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916775380123648 |
|---|---|
| author | Zhao, Yurui Wang, Xiang Liu, Jiahong King, Irwin Huang, Zhitao |
| author_facet | Zhao, Yurui Wang, Xiang Liu, Jiahong King, Irwin Huang, Zhitao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02690 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Geometry Problem Solving in the Large Model Era: A Survey Zhao, Yurui Wang, Xiang Liu, Jiahong King, Irwin Huang, Zhitao Computer Vision and Pattern Recognition Geometric Topology 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. |
| title | Towards Geometry Problem Solving in the Large Model Era: A Survey |
| topic | Computer Vision and Pattern Recognition Geometric Topology |
| url | https://arxiv.org/abs/2506.02690 |