English
Related papers

Related papers: Thor: Wielding Hammers to Integrate Language Model…

200 papers

We introduce a theorem proving algorithm that uses practically no domain heuristics for guiding its connection-style proof search. Instead, it runs many Monte-Carlo simulations guided by reinforcement learning from previous proof attempts.…

Artificial Intelligence · Computer Science 2018-05-22 Cezary Kaliszyk , Josef Urban , Henryk Michalewski , Mirek Olšák

Interactive theorem provers have been used extensively to reason about various software/hardware systems and mathematical theorems. The key challenge when using an interactive prover is finding a suitable sequence of proof steps that will…

Logic in Computer Science · Computer Science 2014-05-15 Thomas Gransden , Neil Walkinshaw , Rajeev Raman

To take advantage of Large Language Model in theorem formalization and proof, we propose a reinforcement learning framework to iteratively optimize the pretrained LLM by rolling out next tactics and comparing them with the expected ones.…

Artificial Intelligence · Computer Science 2025-02-14 Zhiling Luo

Dependently-typed proof assistants furnish expressive foundations for mechanised mathematics and verified software. However, automation for these systems has been either modest in scope or complex in implementation. We aim to improve the…

Logic in Computer Science · Computer Science 2026-02-24 Artjoms Šinkarovs , Michael Rawson

Formal verification using interactive theorem provers ensures high-quality software. However, writing proof scripts for interactive theorem provers is labor-intensive and requires deep expertise. Recent studies have leveraged deep learning…

Logic in Computer Science · Computer Science 2026-04-28 Manqing Zhang , Yunwei Dong , Lingru Zhou , Bingxu Xiao , Yepang Liu

Smart premise selection is essential when using automated reasoning as a tool for large-theory formal proof development. A good method for premise selection in complex mathematical libraries is the application of machine learning to large…

Machine Learning · Computer Science 2014-01-07 Jesse Alama , Tom Heskes , Daniel Kühlwein , Evgeni Tsivtsivadze , Josef Urban

Using an interactive theorem prover to reason about programs involves a sequence of interactions where the user challenges the theorem prover with conjectures. Invariably, many of the conjectures posed are in fact false, and users often…

Software Engineering · Computer Science 2011-10-24 Harsh Raju Chamarthi , Peter C. Dillinger , Matt Kaufmann , Panagiotis Manolios

General-purpose Large Language Models (LLMs) have achieved remarkable success in intelligence, performing comparably to human experts on complex reasoning tasks such as coding and mathematical reasoning. However, generating formal proofs in…

Vampire has been for a long time the strongest first-order automatic theorem prover, widely used for hammer-style proof automation in ITPs such as Mizar, Isabelle, HOL, and Coq. In this work, we considerably improve the performance of…

Artificial Intelligence · Computer Science 2021-05-12 Martin Suda

Theorem provers are important tools for people working in formal verification. There are a myriad of interactive systems available today, with varying features and approaches motivating their development. These design choices impact their…

Logic in Computer Science · Computer Science 2025-09-19 Harrison Oates , Hyeonggeun Yun , Nikhila Gurusinghe

Human mathematicians are often good at recognizing modular and reusable theorems that make complex mathematical results within reach. In this paper, we propose a novel method called theoREm-from-prooF extrACTOR (REFACTOR) for training…

Artificial Intelligence · Computer Science 2024-02-28 Jin Peng Zhou , Yuhuai Wu , Qiyang Li , Roger Grosse

We present a system that utilizes machine learning for tactic proof search in the Coq Proof Assistant. In a similar vein as the TacticToe project for HOL4, our system predicts appropriate tactics and finds proofs in the form of tactic…

Artificial Intelligence · Computer Science 2020-08-04 Lasse Blaauwbroek , Josef Urban , Herman Geuvers

Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically checked. Formal theorem proving systems such as Lean 4 offer automated…

Artificial Intelligence · Computer Science 2026-03-18 Sumanth Varambally , Thomas Voice , Yanchao Sun , Zhifeng Chen , Rose Yu , Ke Ye

When working on intelligent tutor systems designed for mathematics education and its specificities, an interesting objective is to provide relevant help to the students by anticipating their next steps. This can only be done by knowing,…

Artificial Intelligence · Computer Science 2020-03-02 Ludovic Font , Sébastien Cyr , Philippe R. Richard , Michel Gagnon

Traditional language model-based theorem proving assumes that by training on a sufficient amount of formal proof data, a model will learn to prove theorems. Our key observation is that a wealth of informal information that is not present in…

Artificial Intelligence · Computer Science 2025-03-18 Haohan Lin , Zhiqing Sun , Sean Welleck , Yiming Yang

Real number calculations on elementary functions are remarkably difficult to handle in mechanical proofs. In this paper, we show how these calculations can be performed within a theorem prover or proof assistant in a convenient and highly…

Mathematical Software · Computer Science 2007-08-29 Marc Daumas , David Lester , César Muñoz

We study why Tool-Integrated Reasoning (TIR) makes Large Language Models (LLMs) more capable. While LLMs integrated with tools like Python code interpreters show great promise, a principled theory explaining why this paradigm is effective…

Machine Learning · Computer Science 2025-08-27 Heng Lin , Zhongwen Xu

The demand for synthetic data in mathematical reasoning has increased due to its potential to enhance the mathematical capabilities of large language models (LLMs). However, ensuring the validity of intermediate reasoning steps remains a…

Artificial Intelligence · Computer Science 2026-01-19 Joshua Ong Jun Leang , Giwon Hong , Wenda Li , Shay B. Cohen

Large Language Models (LLMs) exhibit impressive performance across various domains but still struggle with arithmetic reasoning tasks. Recent work shows the effectiveness of prompt design methods in enhancing reasoning capabilities.…

Computation and Language · Computer Science 2024-10-11 Wenting Tan , Dongxiao Chen , Jieting Xue , Zihao Wang , Taijie Chen

We describe a "top down" approach for automated theorem proving (ATP). Researchers might usefully investigate the forms of the theorems mathematicians use in practice, carefully examine how they differ and are proved in practice, and code…

Logic in Computer Science · Computer Science 2023-08-09 C. E. Larson , N. Van Cleemput