arXiv AI August 28, 2026 By Jilin Hu, Jianyu Zhang, Yongwang Zhao, Talia Ringer

HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement

HybridProver is a unified framework that combines whole-proof synthesis and tactic-based generation using proof sketches as an intermediate representation. Implemented in Isabelle/HOL, it employs two 7B-scale LLMs trained on optimized Isabelle datasets. On the miniF2F Isabelle benchmark, HybridProver achieved a 73.8% success rate, surpassing the previous state of the art of 61.9%, and ablation studies examined the effects of dataset quality, training settings, and sampling strategies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 16

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

arXiv:2606. 15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources.

By Jierui Zhang, Siyuan Tan, Xinhang Li, Longzhuangzhi Lin, Dailin Li, Chengfeng Gu, Xinping Li, Yaxian Hao, Shengjia Liang, Yuxiang Ren, Wenhao Liu

llms benchmarks

Hugging Face Trending Papers

Jun 8

TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

LLMs have recently achieved strong results on formal proving benchmarks. However, existing evaluations remain heavily concentrated on competition-style problems and often fail to capture how models behave on longer, more dependency-rich mathematical developments.

llms benchmarks

arXiv AI

Jun 16

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

arXiv:2506. 17104v2 Announce Type: replace Abstract: Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas.

By Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

llms benchmarks

arXiv Machine Learning

Jun 25

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

arXiv:2512. 10187v3 Announce Type: replace Abstract: LLMs excel at reasoning, but validating their steps remains challenging.

By Mantas Baksys, Stefan Zetzsche, Olivier Bouissou, Sean B. Holden

llms benchmarks

arXiv AI

Jun 9

TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

arXiv:2606. 09450v1 Announce Type: new Abstract: LLMs have recently achieved strong results on formal proving benchmarks.

By QuocViet Pham, Elvir Karimov, Andrey Galichin, Ivan Oseledets

llms benchmarks

arXiv Machine Learning

Jun 19

Pseudo-Formalization for Automatic Proof Verification

arXiv:2605. 20531v2 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning.

By Slim Barkallah, Luke Bailey, Kaiyue Wen, Mohammed Abouzaid, Tengyu Ma

llms benchmarks

One email a morning, machine-written

Related stories

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving

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

TheoremBench: Evaluating LLMs on Theorem Proving in Formal Mathematics

Pseudo-Formalization for Automatic Proof Verification