arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.07779cs.CLcs.AI
收藏

从求解器到研究:前沿研究中的大语言模型驱动形式数学

From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室)
Eric Jiang, Xiao Liang, Junyi Zhang, Justin Baker, Zhi Zhang, Yingjia Wan, Yubei Li, Jinxi Yu, Mengting Li, Haikang Deng, Alexander Taylor, Rushil Raghavan, Mic… 展开作者

Eric Jiang, Xiao Liang, Junyi Zhang, Justin Baker, Zhi Zhang, Yingjia Wan, Yubei Li, Jinxi Yu, Mengting Li, Haikang Deng, Alexander Taylor, Rushil Raghavan, Michael Simon, Hyunsik Chae, Jia-Chen Gu, Xinjie He, Kyle Hess, Ethan Ji, Yiwen Kou, Tzu-Han Lin, Jiachen Lu, Jack Mauro, Vigyan Sahai, Zheng Tan, Hengli Li, Yikai Zhang, Kyle Zheng, Lunji Zhu, Dong Liu, Jasdeep Sidhu, Isaac Hair, Eniuce Jun, Ying Nian Wu, Andrea L. Bertozzi, Kai-Wei Chang, Raghu Meka, Matthew Sottile, Nanyun Peng, Amit Sahai, Terence Tao, Wei Wang

AI总结:

探讨AI4Math领域进展,指出当前系统处理前沿数学问题有局限。主张从预定义求解器转向研究代理,对该领域进行系统综述,识别现有系统局限性,为AI4Math未来发展规划战略路线图。

摘要:

人工智能在数学领域(AI4Math)的最新进展,特别是大语言模型驱动的定理证明器,通过交互式定理证明(ITP)语言在定义明确的数学问题的形式证明生成方面取得了显著成功。然而,当前系统在处理前沿研究数学问题时仍存在根本限制,如发现新定理或解决开放猜想,这些问题往往是开放式、规定不明确且涉及多层抽象。我们认为,AI4Math系统的下一次飞跃需要从预定义的问题求解器向能够通过严格的形式数学推理应对前沿数学挑战的研究代理进行决定性转变。在本立场文件中,我们对该领域进行了系统综述,涵盖数据集、自动形式化和证明合成。更重要的是,我们确定了现有系统作为数学研究代理的核心局限性,研究了数据集、关系结构、数学探索、工具生态系统和人机协作等方面的问题,为AI4Math的未来勾勒了战略路线图。

英文摘要:

Large language models have made rapid progress in generating machine-checked proofs for well-defined mathematical problems. Extending this progress to research mathematics requires more than solving isolated theorems. Research involves choosing questions, developing definitions and conjectures, connecting results, and combining formal proofs with expert judgment. This survey examines how LLM-driven systems can support these broader activities. We review formal-mathematics tasks, datasets, and autoformalization, and organize proof-generation methods into three overlapping areas: training strategies, inference-time search and adaptation, and agentic workflows. We then examine benchmark results, selected research projects, and platforms for collaborative mathematical work. A central distinction runs throughout the survey: checking a formal proof does not by itself establish that it captures the intended problem or makes a new mathematical contribution. We therefore distinguish theorem benchmarks, repository tasks, formalization projects, and research claims, and discuss the evidence needed to assess each. Finally, we identify five priorities for progress: better data and evaluation, representations of mathematical relationships, conjecture and concept generation, reliable tool integration, and human--AI collaboration. Together, these perspectives connect advances in proof generation to the practical demands of mathematical research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑