paper-with-me

Papers

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

2022-10-21 · Albert Q. Jiang, Sean Welleck, Jin Peng Zhou, Wenda Li, Jiacheng Liu, Mateja Jamnik, Timothée Lacroix, Yuhuai Wu, Guillaume Lample

The formalization of existing mathematical proofs is a notoriously difficult process. Despite decades of research on automation and proof assistants, writing formal proofs remains arduous and only accessible to a few experts. While previous studies to automate formalization focused on powerful search algorithms, no attempts were made to take advantage of available informal proofs. In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems. We investigate two relevant setups where informal proofs are either written by humans or generated by a language model. Our experiments and ablation studies show that large language models are able to produce well-structured formal sketches that follow the same reasoning steps as the informal proofs. Guiding an automated prover with these sketches enhances its performance from 20.9% to 39.3% on a collection of mathematical competition problems.

📄 PDF Abstract BibTeX arXiv:2210.12283

Code (3)

albertqjiang/draft_sketch_prove 공식 구현
facebookresearch/minif2f 공식 구현
rah4927/lean-dojo-mew

Tasks

Automated Theorem ProvingLanguage ModelingLanguage ModellingMathematical Proofs

Similar Papers 제목 키워드 기반

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

2026-03-22 · Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo 외 arxiv

We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose…

Reinforcement Learning

Learning to Reason with Insight for Informal Theorem Proving

2026-04-17 · Yunhe Li, Hao Shi, Bowen Deng, Wei Wang 외 arxiv

Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in natural language processing. In this work…

Mathematical Reasoning

Lectures on Jacques Herbrand as a Logician

2009-02-26 · Claus-Peter Wirth, Joerg Siekmann, Christoph Benzmueller, Serge Autexier

We give some lectures on the work on formal logic of Jacques Herbrand, and sketch his life and his influence on automated theorem proving. The intended audience ranges from students interested in logic over historians to…

Automated Theorem ProvingFormal LogicLEMMATranslation

TheoremForge: Scaling up Formal Data Synthesis with Low-Budget Agentic Workflow

2026-01-24 · Yicheng Tao, Hongteng Xu arxiv

The high cost of agentic workflows in formal mathematics hinders large-scale data synthesis, exacerbating the scarcity of open-source corpora. To address this, we introduce \textbf{TheoremForge}, a cost-effective formal …

FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theory

2025-09-26 · Xiao-Wen Yang, Zihao Zhang, Jianuo Cao, Zhi Zhou 외 arxiv

Large language models (LLMs) have recently demonstrated remarkable progress in formal theorem proving. Yet their ability to serve as practical assistants for mathematicians, filling in missing steps within complex proofs…