AILGDec 14, 2024

Proposing and solving olympiad geometry with guided tree search

arXiv:2412.10673v114 citationsh-index: 14Nat Mach Intell
Originality Incremental advance
AI Analysis

This advances AI in automated theorem proving for geometry, with potential impact on education and competition training, though it is incremental in applying tree search and LLMs to a specific domain.

The paper tackled the challenge of automating theorem discovery and proving in Euclidean geometry for mathematical olympiads, resulting in TongGeometry, which discovered 6.7 billion geometry theorems, proposed 10 to competitions with 3 selected, and solved all problems in IMO-AG-30, outperforming gold medalists.

Mathematics olympiads are prestigious competitions, with problem proposing and solving highly honored. Building artificial intelligence that proposes and solves olympiads presents an unresolved challenge in automated theorem discovery and proving, especially in geometry for its combination of numerical and spatial elements. We introduce TongGeometry, a Euclidean geometry system supporting tree-search-based guided problem proposing and solving. The efficient geometry system establishes the most extensive repository of geometry theorems to date: within the same computational budget as the existing state-of-the-art, TongGeometry discovers 6.7 billion geometry theorems requiring auxiliary constructions, including 4.1 billion exhibiting geometric symmetry. Among them, 10 theorems were proposed to regional mathematical olympiads with 3 of TongGeometry's proposals selected in real competitions, earning spots in a national team qualifying exam or a top civil olympiad in China and the US. Guided by fine-tuned large language models, TongGeometry solved all International Mathematical Olympiad geometry in IMO-AG-30, outperforming gold medalists for the first time. It also surpasses the existing state-of-the-art across a broader spectrum of olympiad-level problems. The full capabilities of the system can be utilized on a consumer-grade machine, making the model more accessible and fostering widespread democratization of its use. By analogy, unlike existing systems that merely solve problems like students, TongGeometry acts like a geometry coach, discovering, presenting, and proving theorems.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes