English
Related papers

Related papers: Ax-Prover: A Deep Reasoning Agentic Framework for …

200 papers

Theorem proving serves as a major testbed for evaluating complex reasoning abilities in large language models (LLMs). However, traditional automated theorem proving (ATP) approaches rely heavily on formal proof systems that poorly align…

Computation and Language · Computer Science 2025-06-04 Ziyin Zhang , Jiahao Xu , Zhiwei He , Tian Liang , Qiuzhi Liu , Yansi Li , Linfeng Song , Zhenwen Liang , Zhuosheng Zhang , Rui Wang , Zhaopeng Tu , Haitao Mi , Dong Yu

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Artificial Intelligence · Computer Science 2025-07-16 Junde Wu , Jiayuan Zhu , Yuyuan Liu , Min Xu , Yueming Jin

Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn…

Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involve training or fine-tuning an LLM on a…

Machine Learning · Computer Science 2025-03-07 Adarsh Kumarappan , Mo Tiwari , Peiyang Song , Robert Joseph George , Chaowei Xiao , Anima Anandkumar

Undergraduate students of artificial intelligence often struggle with representing knowledge as logical sentences. This is a skill that seems to require extensive practice to obtain, suggesting a teaching strategy that involves the…

Computers and Society · Computer Science 2015-07-15 Angelo Kyrilov , David Noelle

In this paper we demonstrate how logic programming systems and Automated first-order logic Theorem Provers (ATPs) can improve the accuracy of Large Language Models (LLMs) for logical reasoning tasks where the baseline performance is given…

Artificial Intelligence · Computer Science 2024-08-08 Lachlan McGinness , Peter Baumgartner

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

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

Automated theorem proving, or more broadly automated reasoning, aims at using computer programs to automatically prove or disprove mathematical theorems and logical statements. It takes on an essential role across a vast array of…

Quantum Physics · Physics 2026-01-14 Zheng-Zhi Sun , Qi Ye , Dong-Ling Deng

Neural theorem proving combines large language models (LLMs) with proof assistants such as Lean, where the correctness of formal proofs can be rigorously verified, leaving no room for hallucination. With existing neural theorem provers…

Artificial Intelligence · Computer Science 2025-05-13 Peiyang Song , Kaiyu Yang , Anima Anandkumar

We propose a minimal agentic baseline that enables systematic comparison across different AI-based theorem prover architectures. This design implements the core features shared among state-of-the-art systems: iterative proof refinement,…

Artificial Intelligence · Computer Science 2026-05-15 Borja Requena , Austin Letson , Krystian Nowakowski , Izan Beltran-Ferreiro , Leopoldo Sarra

Formalizing mathematical proofs using computerized verification languages like Lean 4 has the potential to significantly impact the field of mathematics, it offers prominent capabilities for advancing mathematical reasoning. However,…

Computation and Language · Computer Science 2024-11-11 Xichen Tang

Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model…

Artificial Intelligence · Computer Science 2026-04-20 Chengwu Liu , Yichun Yin , Ye Yuan , Jiaxuan Xie , Botao Li , Siqi Li , Jianhao Shen , Yan Xu , Lifeng Shang , Ming Zhang

Recent advances in large language models have demonstrated impressive capabilities in mathematical formalization. However, existing benchmarks focus on logical verification of declarative propositions, often neglecting the task of…

Logic in Computer Science · Computer Science 2026-02-03 Bowen Yang , Yi Yuan , Chenyi Li , Ziyu Wang , Liangqi Li , Bo Zhang , Zhe Li , Zaiwen Wen

Despite the success of large language models (LLMs), the task of theorem proving still remains one of the hardest reasoning tasks that is far from being fully solved. Prior methods using language models have demonstrated promising results,…

Automated Theorem Proving (ATP) in formal languages is a foundational challenge for AI. While Large Language Models (LLMs) have driven remarkable progress, a significant gap remains between their powerful informal reasoning capabilities and…

Logic in Computer Science · Computer Science 2025-07-10 Zhenwen Liang , Linfeng Song , Yang Li , Tao Yang , Feng Zhang , Haitao Mi , Dong Yu

Process mining provides powerful insights into organizational workflows, but extracting these insights typically requires expertise in specialized query languages and data science tools. Large Language Models (LLMs) offer the potential to…

Artificial Intelligence · Computer Science 2026-03-17 Anton Antonov , Humam Kourani , Alessandro Berti , Gyunam Park , Wil M. P. van der Aalst

We introduce DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start…

The problem-solving in automated theorem proving (ATP) can be interpreted as a search problem where the prover constructs a proof tree step by step. In this paper, we propose a deep reinforcement learning algorithm for proof search in…

Machine Learning · Computer Science 2018-11-05 Mitsuru Kusumoto , Keisuke Yahata , Masahiro Sakai

AI agents have shown initial promise in automating mathematical theorem proving in proof assistants such as Lean. The same proof assistants can be used to verify the correctness of code by pairing code with specifications and proofs that…

Software Engineering · Computer Science 2024-10-11 Evan Lohn , Sean Welleck