paper-with-me

홈 › Papers

MINIF2F-DAFNY: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification

2025-12-11 · Mantas Baksys, Stefan Zetzsche, Olivier Bouissou, Sean B. Holden arxiv

LLMs excel at reasoning, but validating their steps remains challenging. Formal verification offers a solution through mechanically checkable proofs. Interactive theorem provers (ITPs) dominate mathematical reasoning but require detailed low-level proof steps, while auto-active verifiers offer automation but focus on software verification. Recent work has begun bridging this divide by evaluating LLMs for software verification in ITPs, but the complementary direction, LLMs for mathematical theorem proving in auto-active verifiers, remains unexplored. We present MINIF2F-DAFNY, the first translation of the widely-used mathematical benchmark miniF2F to an auto-active verifier: Dafny. We find that Dafny's automation alone solves 39-44% of problems with empty proofs, whereas many require substantial proof guidance in ITPs. We evaluate 8 off-the-shelf LLMs on proof generation, with the best model (Claude Opus 4.6) achieving 62.7% cumulative pass@4 on the full test set, improving over the 38.9% empty-proof baseline by 23.8 percentage points. These results show that auto-active verification offers a complementary empirical setting for AI-assisted mathematical reasoning, where LLMs provide high-level guidance while SMT automation handles low-level details. Our benchmark and evaluation infrastructure are publicly available on https://github.com/dafny-lang/miniF2F.

📄 PDF Abstract BibTeX arXiv:2512.10187

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics

2021-08-31 · ICLR 2022 4 · Kunhao Zheng, Jesse Michael Han, Stanislas Polu

We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Le…

Automated Theorem Proving

HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving

2024-12-30 · Yang Li, Dong Du, Linfeng Song, Chen Li 외

We introduce HunyuanProver, an language model finetuned from the Hunyuan 7B for interactive automatic theorem proving with LEAN4. To alleviate the data sparsity issue, we design a scalable framework to iterative synthesi…

Automated Theorem ProvingLanguage ModelingLanguage Modelling

miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward

2025-11-05 · Azim Ospanov, Farzan Farnia, Roozbeh Yousefzadeh arxiv

We perform a thorough analysis of the formal and informal statements in the miniF2F benchmark from the perspective of an AI system that is tasked to participate in a math Olympiad consisting of the problems in miniF2F. I…

LEGO-Prover: Neural Theorem Proving with Growing Libraries

2023-10-01 · Haiming Wang, Huajian Xin, Chuanyang Zheng, Lin Li 외

Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated…

Automated Theorem Proving

miniCTX: Neural Theorem Proving with (Long-)Contexts

2024-08-05 · Jiewen Hu, Thomas Zhu, Sean Welleck

Real-world formal theorem proving often depends on a wealth of context, including definitions, lemmas, comments, file structure, and other information. We introduce miniCTX, which tests a model's ability to prove formal …

Automated Theorem Proving