English
Related papers

Related papers: MerLean-Prover: A Recursive Looping Harness for Le…

200 papers

Applying Gr\"obner basis theory to concrete problems in Lean 4 remains difficult since the current formalization of multivariate polynomials is based on a non-computable representation and is therefore not suitable for efficient symbolic…

Logic in Computer Science · Computer Science 2026-04-16 Hao Shen , Junyu Guo , Junqi Liu , Lihong Zhi

Advances in training, post-training, and inference-time methods have enabled frontier reasoning models to win gold medals in math competitions and settle challenging open problems. Gaining trust in the responses of these models requires…

Machine Learning · Computer Science 2026-04-06 Aaditya Naik , Guruprerana Shabadi , Rajeev Alur , Mayur Naik

One of the main issues in proof certification is that different theorem provers, even when designed for the same logic, tend to use different proof formalisms and produce outputs in different formats. The project ProofCert promotes the…

Logic in Computer Science · Computer Science 2019-10-09 Tomer Libal , Marco Volpe

Large language models (LLMs) have become capable mathematical problem-solvers, often producing correct proofs for challenging problems. However, correctness alone is not sufficient: mathematical proofs should also be clear, concise,…

Computation and Language · Computer Science 2026-05-12 Ivo Petrov , Jasper Dekoninck , Dimitar I. Dimitrov , Martin Vechev

Automated theorem proving with large language models in Lean 4 is commonly approached through either step-level tactic prediction with tree search or whole-proof generation. These two paradigms represent opposite granularities for…

Artificial Intelligence · Computer Science 2026-05-13 Shuo Xu , Jiakun Zhang , Junyu Lai , Chun Cao , Jingwei Xu

Machine-assisted theorem proving refers to the process of conducting structured reasoning to automatically generate proofs for mathematical theorems. Recently, there has been a surge of interest in using machine learning models in…

Logic in Computer Science · Computer Science 2025-02-03 Leni Aniva , Chuyue Sun , Brando Miranda , Clark Barrett , Sanmi Koyejo

Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligence and cognitive science. As LLMs are increasingly…

Computation and Language · Computer Science 2026-04-03 Linyang He , Qiyao Yu , Hanze Dong , Baohao Liao , Xinxing Xu , Micah Goldblum , Jiang Bian , Nima Mesgarani

Recent work by Clark et al. (2020) shows that transformers can act as 'soft theorem provers' by answering questions over explicitly provided knowledge in natural language. In our work, we take a step closer to emulating formal theorem…

Computation and Language · Computer Science 2020-10-07 Swarnadeep Saha , Sayan Ghosh , Shashank Srivastava , Mohit Bansal

As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no longer tell whether those tokens buy useful reasoning, recovery from hard instances, or unnecessary…

Computation and Language · Computer Science 2026-05-19 Daniel Kaiser , Arnoldo Frigessi , Ali Ramezani-Kebrya , Benjamin Ricaud

Understanding how and why large language models (LLMs) fail is becoming a central challenge as models rapidly evolve and static evaluations fall behind. While automated probing has been enabled by dynamic test generation, existing…

Computation and Language · Computer Science 2026-02-16 Yue Huang , Zhengzhe Jiang , Yuchen Ma , Yu Jiang , Xiangqi Wang , Yujun Zhou , Yuexing Hao , Kehan Guo , Pin-Yu Chen , Stefan Feuerriegel , Xiangliang Zhang

Large language models can now generate substantial code and draft research text, but research-software projects require more than either artifact alone. The mathematical thesis, executable system, benchmark surface, and public claims must…

Software Engineering · Computer Science 2026-05-04 Halley Young , Nikolaj Björner

Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guide the proof process. Modern Multimodal…

Computation and Language · Computer Science 2025-06-09 Zhitao He , Zongwei Lyu , Dazhong Chen , Dadi Guo , Yi R. Fung

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…

Computation and Language · Computer Science 2025-12-03 Ziyan Wang , Enmao Diao , Qi Le , Pu Wang , Guanchu Wang , Minwoo Lee , Shu-ping Yeh , Li Yang

AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…

Multiagent Systems · Computer Science 2026-05-26 Fouad Bousetouane

Software testing plays a critical role in ensuring that systems behave as intended. However, existing automated testing approaches struggle to match the capabilities of human engineers due to key limitations such as test locality, lack of…

Software Engineering · Computer Science 2025-06-16 Kangping Xu , Yifan Luo , Yang Yuan , Andrew Chi-Chih Yao

The research in AI-based formal mathematical reasoning has shown an unstoppable growth trend. These studies have excelled in mathematical competitions like IMO and have made significant progress. This paper focuses on formal verification,…

Artificial Intelligence · Computer Science 2025-06-10 Jialun Cao , Yaojie Lu , Meiziniu Li , Haoyang Ma , Haokun Li , Mengda He , Cheng Wen , Le Sun , Hongyu Zhang , Shengchao Qin , Shing-Chi Cheung , Cong Tian

Ensuring correctness is a pivotal aspect of software engineering. Among the various strategies available, software verification offers a definitive assurance of correctness. Nevertheless, writing verification proofs is resource-intensive…

Software Engineering · Computer Science 2024-06-06 Lichen Zhang , Shuai Lu , Nan Duan

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

We present a prototype of an integrated reasoning environment for educational purposes. The presented tool is a fragment of a proof assistant and automated theorem prover. We describe the existing and planned functionality of the theorem…

Human-Computer Interaction · Computer Science 2018-03-06 Mario Frank , Christoph Kreitz

Reinforcement Learning with Verifiable Rewards (RLVR) has advanced LLM reasoning, but remains constrained by inefficient exploration under limited rollout budgets, leading to low sampling success and unstable training in complex tasks. We…

Machine Learning · Computer Science 2026-04-21 Yiju Guo , Tianyi Hu , Zexu Sun , Yankai Lin