MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4
On the map: LLM agents and tool use → Educational agents and math problem solving
Abstract (arXiv)
We present MechGeo, a Mathlib native agentic framework that jointly addresses faithful autoformalization and certified proof construction for Euclidean geometry. In this framework, GeoFormalizer represents informal problems in GeoIR, deterministically translates them into Lean 4, and iteratively repairs candidate statements using structural diagnostics and semantic evaluation. GeoProver constructs geometric proof plans, derives intermediate lemmas, and selectively algebraizes suitable subgoals through a library verified in Lean. Singular or SymPy may generate algebraic certificates, but all resulting proofs and counterexamples are checked by Lean's kernel. Experiments across seven LLM backbones show substantial improvements in autoformalization, particularly for models with weaker direct translation performance. On 43 historical IMO geometry problems, GeoFormalizer generates formal statements that GeoProver proves in 29 cases; for the remaining 14, it constructs counterexamples verified in Lean and proves all repaired statements after expert correction. Together with IMO 2026 Problem 2, this yields, to the best of our knowledge, the largest reported collection of automated, kernel-checked Lean proofs for IMO geometry problems. On the 14 geometry statements in LEAP's Lean-IMO-Bench, MechGeo proves 12 for the first time, formally refutes the remaining two, and proves both repaired statements. These results establish counterexample guided diagnosis, geometric reasoning, and certified symbolic computation as a practical foundation for trustworthy formal geometry.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use. Builds on 14 of its 35 references that are in the map. First posted on arXiv 3 Aug 2026.
Builds on
14 of 35 references.
Closest ancestors · 3
Same direction, newest first
- 2026Beyond the Library: An Agentic Framework for Autoformalizing Research Mathematics30 Jun
- 2026LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks2 Jun
- 2026Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics20 Jan
Other references · 11
- 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
- 2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decompositioncited by 287
- 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competitioncited by 165
- 2025Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correctioncited by 154
- 2025Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2cited by 97
- 2025Hilbert: Recursively Building Formal Proofs with Informal Reasoningcited by 60
- 2024Proposing and solving olympiad geometry with guided tree searchcited by 19
- 2024Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometrycited by 11
- 2026AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilitiescited by 5
- 2017Proof-checking Euclidcited by 4
- 2026Euclean: Automated Geometry Problem Formalization with Unified Verification in Leancited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025LeanGeo: Formalizing Competitional Geometry problems in Lean
- 2026SHADOWBENCH: Toward Reliable Automatic Evaluation of Semantic Alignment in Autoformalization
- 2026M2F: Automated Formalization of Mathematical Literature at Scale
- 2026GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams
- 2025GeoFM: Enhancing Geometric Reasoning of MLLMs via Synthetic Data Generation through Formal Language
- 2026Construction-Verification: A Benchmark for Applied Mathematics in Lean 4
- 2024FGeo-TP: A Language Model-Enhanced Solver for Geometry Problems
- 2026GeoReform: Reflective Formalization Evolution for Multimodal Geometry Problem Solving