AI Paper Atlas

Research map / Large language models / Agents, code and math

Euclean: Automated Geometry Problem Formalization with Unified Verification in Lean

Linbin Tang, Jingyan You, Zilin Kang, Hanzhang Liu, Sophia Zhang, Zenan Li, Chenrui Cao, Liangcheng Song, Jiaao Wu, Xian Zhang, Fan Yang

ICML 2026 · Large language models › Agents, code and math · approach: Retrieval-augmented formal theorem proving · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add concept formalization mapping to Mathlib primitives (ablation)Euclean pipeline · OMNI-Geometry (30 problems)compiling candidates (of 960): 125 -> 254Improved
add iterative compiler-feedback repair (ablation)Euclean pipeline · OMNI-Geometry (30 problems)compiling candidates (of 960): 254 -> 465Improved
add constraint formalization mapping (ablation)Euclean pipeline · OMNI-Geometry (30 problems)compiling candidates (of 960): 465 -> 500Improved
add Prove-First configuration anchoring (ablation)Euclean pipeline · OMNI-Geometry (30 problems)compiling candidates (of 960): 500 -> 480Hurt
add Prove-First configuration anchoring (ablation)Euclean pipeline · OMNI-Geometry (30 problems, human Pass@3 paired)semantic faithfulness (wins vs losses): 7 wins, 3 losses (10 both correct, 10 both incorrect)Improved
sample five candidates (TOP5) instead of first only (TOP1)Euclean · OMNI-Geometry (180 problems, difficulty 4.0+)human-judged accuracy (%): 48.89 -> 73.33Improved
increase problem difficulty to 8.0+Euclean · OMNI-Geometry (human eval)TOP1 accuracy (%): 50.94 -> 20.00Hurt
fine-tune Goedel v2 with SFT on proofs of Euclean-formalized geometryGoedel v2 8B · Numina-Geometryproof Pass@1 (%): 13.6 -> 15.1Improved
use DPO on pass/fail pairs instead of SFT (ablation)Goedel v2 8B · Numina-Geometryproof Pass@1 (%): 15.1 (SFT) vs 15.0 (DPO)No clear effect
fine-tune DeepSeek-Prover-V2-7B with SFT on Euclean dataDeepSeek-Prover-V2-7B · Numina-Geometryproof Pass@1: 13.4% -> 15.0%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy