English
Related papers

Related papers: OProver: A Unified Framework for Agentic Formal Th…

200 papers

We introduce Goedel-Prover-V2, a series of open-source language models that set a new state-of-the-art in automated theorem proving. Built on the standard expert iteration and reinforcement learning pipeline, our approach incorporates three…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Artificial Intelligence · Computer Science 2026-04-10 Wenhao Yuan , Chenchen Lin , Jian Chen , Jinfeng Xu , Xuehe Wang , Edith Cheuk Han Ngai

Building software that is correct by construction is a long-standing goal in software engineering, as it ensures reliability during design and development rather than after deployment. Formal methods realize this vision by enabling the…

Software Engineering · Computer Science 2026-05-19 Hongshu Wang , Xinyue Zuo , Yuhan Sun , Qin Li , Yamine Ait Ameur , Jin Song Dong

Automated Theorem Proving (ATP) in formal languages remains a formidable challenge in AI, demanding rigorous logical deduction and navigating vast search spaces. While large language models (LLMs) have shown promising performance, existing…

Artificial Intelligence · Computer Science 2025-05-19 Zhenwen Liang , Linfeng Song , Yang Li , Tao Yang , Feng Zhang , Haitao Mi , Dong Yu

Theorem proving is a fundamental aspect of mathematics, spanning from informal reasoning in natural language to rigorous derivations in formal systems. In recent years, the advancement of deep learning, especially the emergence of large…

Artificial Intelligence · Computer Science 2024-08-23 Zhaoyu Li , Jialiang Sun , Logan Murphy , Qidong Su , Zenan Li , Xian Zhang , Kaiyu Yang , Xujie Si

Formal theorem proving (FTP) has emerged as a critical foundation for evaluating the reasoning capabilities of large language models, enabling automated verification of mathematical proofs at scale. However, progress has been constrained by…

Logic in Computer Science · Computer Science 2026-05-19 Terry Jingchen Zhang , Wenyuan Jiang , Rongchuan Liu , Yisong Wang , Junran Yang , Ning Wang , Nicole Ni , Yinya Huang , Mrinmaya Sachan

RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A…

Artificial Intelligence · Computer Science 2026-05-19 Zachary Burton

Large Language Model (LLM)-based agentic systems, often comprising multiple models, complex tool invocations, and orchestration protocols, substantially outperform monolithic agents. Yet this very sophistication amplifies their fragility,…

Computation and Language · Computer Science 2025-09-05 Guibin Zhang , Junhao Wang , Junjie Chen , Wangchunshu Zhou , Kun Wang , Shuicheng Yan

LLM-generated explanations can make technical content more accessible, but there is a ceiling on what they can support interactively. Because LLM outputs are static text, they cannot be executed or stepped through. We argue that grounding…

Human-Computer Interaction · Computer Science 2026-04-13 Hita Kambhamettu , Will Crichton , Sean Welleck , Harrison Goldstein , Andrew Head

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

With the development of artificial intelligence (AI), large language models (LLM) are widely used in many fields. However, the reasoning ability of LLM is still very limited when it comes to mathematical reasoning. Mathematics plays an…

Computation and Language · Computer Science 2024-08-06 Wenbei Xie , Donglin Liu , Haoran Yan , Wenjie Wu , Zongyang Liu

Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback is often expensive and slow to obtain, making online reinforcement learning (RL) impractical. High-coverage hardware verification…

Artificial Intelligence · Computer Science 2026-02-27 Hejia Zhang , Zhongming Yu , Chia-Tung Ho , Haoxing Ren , Brucek Khailany , Jishen Zhao

The rise of reasoning models necessitates large-scale verifiable data, for which programming tasks serve as an ideal source. However, while competitive programming platforms provide abundant problems and solutions, high-quality test cases…

Software Engineering · Computer Science 2026-01-21 Jianfeng Cai , Jinhua Zhu , Ruopei Sun , Kangwen Zhao , Dongyun Xue , Mingxiao Feng , Wengang Zhou , Houqiang Li

Auto-active verifiers provide a level of automation intermediate between fully automatic and interactive: users supply code with annotations as input while benefiting from a high level of automation in the back-end. This paper presents…

Logic in Computer Science · Computer Science 2015-09-01 Julian Tschannen , Carlo A. Furia , Martin Nordio , Nadia Polikarpova

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely language-driven, relying…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Dongyang Chen , Chaoyang Wang , Dezhao Su , Xi Xiao , Zeyu Zhang , Jing Xiong , Qing Li , Yuzhang Shang , Shichao Kan

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

We introduce MerLean, a fully automated agentic framework for autoformalization in quantum computation. MerLean extracts mathematical statements from \LaTeX{} source files, formalizes them into verified Lean~4 code built on Mathlib, and…

Logic in Computer Science · Computer Science 2026-02-19 Yuanjie Ren , Jinzheng Li , Yidi Qi

Large Language Models (LLMs) have demonstrated significant promise in formal theorem proving. In this study, we investigate the ability of LLMs to discover novel theorems and produce verified proofs. We propose a pipeline called…

Machine Learning · Computer Science 2026-05-07 Kazumi Kasaura , Naoto Onda , Yuta Oriike , Masaya Taniguchi , Akiyoshi Sannai , Sho Sonoda

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 synthesize data with low…

Artificial Intelligence · Computer Science 2025-03-24 Yang Li , Dong Du , Linfeng Song , Chen Li , Weikang Wang , Tao Yang , Haitao Mi

Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i.e. proof steps) to search through proof states. The current model, while trained solely on successful…

Artificial Intelligence · Computer Science 2024-07-31 Chenyang An , Zhibo Chen , Qihao Ye , Emily First , Letian Peng , Jiayun Zhang , Zihan Wang , Sorin Lerner , Jingbo Shang