Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
Google Research(谷歌研究院);Carnegie Mellon University(卡内基梅隆大学);Purdue University(普渡大学);University of Southern California(南加州大学);Harvard University(哈佛大学);MIT(麻省理工学院);Illinois Institute of Technology(伊利诺伊理工学院);Rutgers University(罗格斯大学);University of Michigan(密歇根大学);University of California, Irvine(加州大学欧文分校);Texas A&M University(德州农工大学);National Institute of Informatics(国立信息学研究所);The University of Tokyo(东京大学);EPFL(洛桑联邦理工学院);University of Maryland, College Park(马里兰大学帕克分校);Nanyang Technological University(南洋理工大学);Bar-Ilan University(巴伊兰大学)
David P. Woodruff, Vincent Cohen-Addad, Lalit Jain, Jieming Mao, Song Zuo, MohammadHossein Bateni, Simina Branzei, Michael P. Brenner, Lin Chen, Ying Feng, Lanc… 展开作者
David P. Woodruff, Vincent Cohen-Addad, Lalit Jain, Jieming Mao, Song Zuo, MohammadHossein Bateni, Simina Branzei, Michael P. Brenner, Lin Chen, Ying Feng, Lance Fortnow, Gang Fu, Ziyi Guan, Zahra Hadizadeh, Mohammad T. Hajiaghayi, Mahdi JafariRaviz, Adel Javanmard, Karthik C. S., Ken-ichi Kawarabayashi, Ravi Kumar, Silvio Lattanzi, Euiwoong Lee, Yi Li, Ioannis Panageas, Dimitris Paparas, Benjamin Przybocki, Bernardo Subercaseaux, Ola Svensson, Shayan Taherijam, Xuan Wu, Eylon Yogev, Morteza Zadimoghaddam, Samson Zhou, Yossi Matias, James Manyika, Vahab Mirrokni
备注:
The changes over version 2 are that we cleaned up the last paragraph on color-coding at the end of section 2. Also, for section 6.1 we added a reference to followup work of the authors, and other minor edits in that section
近年来,大语言模型(LLMs)的进步为加速科学研究开辟了新途径。尽管模型在协助日常任务方面越来越有能力,但其在贡献于新颖的、专家级别的数学发现方面的能力仍不明确。我们呈现了一组案例研究,展示了研究人员如何成功与高级AI模型(特别是谷歌的Gemini系列模型,特别是Gemini Deep Think及其高级变体)合作,解决开放性问题、反驳猜想并生成新证明,涵盖理论计算机科学在内的多个领域,以及经济学、优化和物理等其他领域。基于这些经验,我们提取了有效的人工智能协作在理论研究中的常见技术,如迭代完善、问题分解和跨学科知识转移。尽管大多数结果源于这种互动、对话式的方法,我们还强调了一些超越标准聊天界面的特定实例。这些包括将模型部署为严谨的对抗性审阅者以检测现有证明中的细微缺陷,以及将其嵌入一个
英文摘要:
Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to contribute to novel, expert-level mathematical discovery is less understood. We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models, specifically Google's Gemini-based models (in particular Gemini Deep Think and its advanced variants), to solve open problems, refute conjectures, and generate new proofs across diverse areas in theoretical computer science, as well as other areas such as economics, optimization, and physics. Based on these experiences, we extract common techniques for effective human-AI collaboration in theoretical research, such as iterative refinement, problem decomposition, and cross-disciplinary knowledge transfer. While the majority of our results stem from this interactive, conversational methodology, we also highlight specific instances that push beyond standard chat interfaces. These include deploying the model as a rigorous adversarial reviewer to detect subtle flaws in existing proofs, and embedding it within a "neuro-symbolic" loop that autonomously writes and executes code to verify complex derivations. Together, these examples highlight the potential of AI not just as a tool for automation, but as a versatile, genuine partner in the creative process of scientific discovery.
ChatGPT and Gemini participated in the Korean College Scholastic Ability Test -- Earth Science I
Institute for Research Excellence in Learning Sciences(学习科学卓越研究所);Seoul National University(首尔大学);National Taiwan Normal University(台湾师范大学);Universitas Negeri Malang(玛琅国立大学)
SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE(普遍知识处理实验室(UKP实验室)、计算机科学系、德累斯顿技术大学和应用网络安全国家研究中心ATHENE)
Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts
Information Sciences Institute, University of Southern California(南加州大学信息科学学院);Iovine and Young Academy, University of Southern California(南加州大学约万与杨学院);In Vivo Group
Google(谷歌);Google DeepMind(谷歌DeepMind);University of Chicago(芝加哥大学);CUNEF Universidad(西班牙金融研究大学);MIT FutureTech(麻省理工学院未来科技);University of Oxford(牛津大学);Carnegie Mellon University(卡内基梅隆大学);University of Pennsylvania(宾夕法尼亚大学)
ProtoMed-LLM: An Automatic Evaluation Framework for Large Language Models in Medical Protocol Formulation
University of Texas at Austin(得克萨斯大学奥斯汀分校);Ulsan National Institute of Science and Technology(蔚山国家科学技术研究院);Korea Institute of Science and Technology (KIST) Europe(韩国科学技术研究院欧洲分院)
Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
Paul G. Allen School of Computer Science \& Engineering University of Washington Seattle WA USA;The Information School University of Washington Allen Institute for AI Seattle WA USA;Allen Institute for AI Seattle WA USA;University of Washington;Allen Institute for AI
Accelerating scientific discovery with Co-Scientist
Google Cloud AI Research(谷歌云人工智能研究);Google DeepMind(谷歌DeepMind);Google Research(谷歌研究);Stanford University School of Medicine(斯坦福大学医学院);Houston Methodist(休斯顿卫理公会医院);Sequome;Fleming Initiative and Imperial College London(弗莱明倡议与伦敦帝国理工学院)
Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Washington(华盛顿大学);Yale University(耶鲁大学);New York University(纽约大学);Carnegie Mellon University(卡内基梅隆大学)