Automatically Building Diagrams for Olympiad Geometry Problems
Not on the map. Why?
Abstract (arXiv)
We present a method for automatically building diagrams for olympiad-level geometry problems and implement our approach in a new open-source software tool, the Geometry Model Builder (GMB). Central to our method is a new domain-specific language, the Geometry Model-Building Language (GMBL), for specifying geometry problems along with additional metadata useful for building diagrams. A GMBL program specifies (1) how to parameterize geometric objects (or sets of geometric objects) and initialize these parameterized quantities, (2) which quantities to compute directly from other quantities, and (3) additional constraints to accumulate into a (differentiable) loss function. A GMBL program induces a (usually) tractable numerical optimization problem whose solutions correspond to diagrams of the original problem statement, and that we can solve reliably using gradient descent. Of the 39 geometry problems since 2000 appearing in the International Mathematical Olympiad, 36 can be expressed in our logic and our system can produce diagrams for 94% of them on average. To the best of our knowledge, our method is the first in automated geometry diagram construction to generate models for such complex problems.
Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 1; 2025: 5; 2026: 2.
8 papers.
- 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2cited by 95
- 2024Diagram Formalization Enhanced Multi-Modal Geometry Problem Solvercited by 11
- 2025NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data Generationcited by 10
- 2025A Survey of Deep Learning for Geometry Problem Solvingcited by 4
- 2025GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Languagecited by 3
- 2026Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learningcited by 1
- 2026GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Languagecited by 1
- 2025Geometric Reasoning in the Embedding Spacecited by 0
- 2026GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language13 May 2026
- 2026Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learning26 Feb 2026
- 2025GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language31 Oct 2025
- 2025A Survey of Deep Learning for Geometry Problem Solving16 Jul 2025
- 2025NeSyGeo: A Neuro-Symbolic Framework for Multimodal Geometric Reasoning Data Generation21 May 2025
- 2025Geometric Reasoning in the Embedding Space2 Apr 2025
- 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry25 Feb 2025
- 2024Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver6 Sep 2024