Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery
Google Research（谷歌研究）；School of Engineering and Applied Sciences, Harvard University（工程与应用科学学院，哈佛大学）；School of Computer Science, Carnegie Mellon University（计算机科学学院，卡内基梅隆大学）
Michael P. Brenner, Vincent Cohen-Addad, David Woodruff
本文证明人工智能可以通过自主解决理论物理中的一个开放问题来加速数学发现。我们提出了一种混合系统，结合Gemini Deep Think大型语言模型和系统化的树搜索（TS）框架以及自动数值反馈，成功推导出宇宙弦发射的引力辐射功率谱的新、精确的解析解。具体来说，该代理评估了任意环形几何的核积分I(N,α)，直接改进了最近的AI辅助尝试[BCE+25]，后者仅得到了部分渐近解。为了验证我们关于AI加速发现的方法论主张并确保透明度，我们详细说明了系统提示、搜索约束以及间歇性反馈循环，这些指导了模型。代理识别出一套6种不同的解析方法，其中最优雅的一种将核在Gegenbauer多项式C_l^(3/2)中展开，自然吸收积分的奇点。这些方法导致了I(N,α)在大N处的渐近结果，既与数值结果一致，也与量子场论的连续费曼参数化相连接。我们详细说明了使这一发现成为可能的算法方法以及由此产生的数学推导。
英文摘要：
This paper demonstrates that artificial intelligence can accelerate mathematical discovery by autonomously solving an open problem in theoretical physics. We present a neuro-symbolic system, combining the Gemini Deep Think large language model with a systematic Tree Search (TS) framework and automated numerical feedback, that successfully derived novel, exact analytical solutions for the power spectrum of gravitational radiation emitted by cosmic strings. Specifically, the agent evaluated the core integral $I(N,α)$ for arbitrary loop geometries, directly improving upon recent AI-assisted attempts \cite{BCE+25} that only yielded partial asymptotic solutions. To substantiate our methodological claims regarding AI-accelerated discovery and to ensure transparency, we detail system prompts, search constraints, and intermittent feedback loops that guided the model. The agent identified a suite of 6 different analytical methods, the most elegant of which expands the kernel in Gegenbauer polynomials $C_l^{(3/2)}$ to naturally absorb the integrand's singularities. The methods lead to an asymptotic result for $I(N,α)$ at large $N$ that both agrees with numerical results and also connects to the continuous Feynman parameterization of Quantum Field Theory. We detail both the algorithmic methodology that enabled this discovery and the resulting mathematical derivations.
AI-assisted Knowledge Discovery in Biomedical Literature to Support Decision-making in Precision Oncology
Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院西德尼·金梅尔综合癌症中心）；Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院）
Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
University of Technology Nuremberg (UTN)（图恩大学（UTN））；University of Tübingen, Tübingen AI Center（图宾根大学，图宾根人工智能中心）；TIB Leibniz Information Centre for Science and Technology（莱比锡信息科学与技术研究中心）；Austrian Research Institute for Artificial Intelligence（奥地利人工智能研究所）；IT:U Interdisciplinary Transformation University Austria（奥地利 interdisciplinary transformation 大学）；University of Hamburg（汉堡大学）；University of Manchester（曼彻斯特大学）；University of Sheffield（谢菲尔德大学）；University of Aberdeen（阿伯丁大学）；University of Manitoba（曼尼托巴大学）
When Rating Scales Fall Short: LLM-Assisted Discovery of ADHD Signals in Turkish Teacher Narratives
Department of Computer Science, University of Illinois Chicago（伊利诺伊大学芝加哥分校计算机科学系）；Department of Child and Adolescent Psychiatry, Gazi University（加齐大学儿童与青少年精神病学系）
Large language model-assisted discovery of cohorts from scientific literature
University Hospital Frankfurt, Goethe University Frankfurt（法兰克福大学医院，法兰克福大学）；Goethe University Frankfurt（法兰克福大学）；The Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心）
LITA: An Efficient LLM-assisted Iterative Topic Augmentation Framework
Department of Biomedical Informatics & Data Science, Yale University（生物医学信息学与数据科学系，耶鲁大学）；Department of Information Management, National Sun Yat-sen University（信息管理系，National Sun Yat-sen University）
LLM-HyPZ: Hardware Vulnerability Discovery using an LLM-Assisted Hybrid Platform for Zero-Shot Knowledge Extraction and Refinement
Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, USA（电气与计算机工程系，亚利桑那大学）；Department of Systems and Industrial Engineering, University of Arizona, Tucson, AZ, USA（系统与工业工程系，亚利桑那大学）；College of Information Science, University of Arizona, Tucson, AZ, USA（信息科学学院，亚利桑那大学）；School of Electrical Engineering and Computer Science, University of North Dakota, Grand Forks, ND, USA（电气工程与计算机科学学院，北达科他大学）；Department of Computer Science, University of California Davis, CA, USA（计算机科学系，加州大学戴维斯分校）
Scalable Quantum State Preparation via Large-Language-Model-Driven Discovery
School of Physics, Peking University（北京大学物理学院）；Center for High Energy Physics, Peking University（北京大学高能物理中心）；Institute of High Energy Physics, Chinese Academy of Sciences（中国科学院高能物理研究所）；Center of Advanced Quantum Studies, School of Physics and Astronomy, Beijing Normal University（北京师范大学物理天文学院先进量子研究中心）；Key Laboratory of Multi-scale Spin Physics, Ministry of Education, Beijing Normal University（北京师范大学教育部多尺度自旋物理重点实验室）
Solving with GeoGebra Discovery an Austrian Mathematics Olympiad problem: Lessons Learned
Universidad Rey Juan Carlos（胡安·卡洛斯国王大学）；The Private University College of Education of the Diocese of Linz（林茨教区私立教育学院）；Universidad Antonio de Nebrija（安东尼奥·德·内布里哈大学）
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）；INRIA Bordeaux Sud-Ouest（法国国家信息与自动化研究所波尔多西南分部）
Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems
School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）；Institute of Marine Science and Technology, Shandong University（山东大学海洋科学与技术研究院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Centre for Frontier AI Research, Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究所前沿人工智能研究中心）
AI-Assisted Discovery and Construction of a Counterexample to the Convergence of Three-Block ADMM with the Identity Matrix as its Third Constraint Block
School of Mathematical Sciences, East China Normal University（华东师范大学数学科学学院）
Symmetry and AI-assisted discovery of magic-state factories
Joint Center for Quantum Information and Computer Science（量子信息与计算机科学联合中心）；NIST（美国国家标准与技术研究院）；University of Maryland（马里兰大学）；IBM Quantum（IBM量子）；IBM T.J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Center for Theoretical Physics（理论物理中心）；Leinweber Institute（莱因韦伯研究所）；Massachusetts Institute of Technology（麻省理工学院）
