With the accumulation of data at an unprecedented rate, its potential to fuel scientific discovery is growing exponentially. This position paper urges the Machine Learning (ML) community to exploit the capabilities of large generative models (LGMs) to develop automated systems for end-to-end data-driven discovery -- a paradigm encompassing the search and verification of hypotheses purely from a set of provided datasets, without the need for additional data collection or physical experiments. We first outline several desiderata for an ideal data-driven discovery system. Then, through DATAVOYAGER, a proof-of-concept utilizing GPT-4, we demonstrate how LGMs fulfill several of these desiderata -- a feat previously unattainable -- while also highlighting important limitations in the current system that open up opportunities for novel ML research. We contend that achieving accurate, reliable, and robust end-to-end discovery systems solely through the current capabilities of LGMs is challenging. We instead advocate for fail-proof tool integration, along with active user moderation through feedback mechanisms, to foster data-driven scientific discoveries with efficiency and reproducibility.
Generative Chemical Language Models for Energetic Materials Discovery
Theoretical Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室理论部）；Weapon Stockpile Modernization Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室武器库存现代化部）；Computing and Artificial Intelligence Division, Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室计算与人工智能部）
Generative Discovery of Partial Differential Equations by Learning from Math Handbooks
Eastern Institute of Technology（东方理工）；Tsinghua University（清华大学）；Ocean University of China（中国海洋大学）；Imperial College London（伦敦帝国理工学院）；University of Oxford（牛津大学）；University of Manchester（曼彻斯特大学）；Peking University（北京大学）；Lingnan University（岭南大学）
Artificial Intelligence and Generative Models for Materials Discovery -- A Review
Institute of Sustainability for Chemicals, Energy and Environment (ISCE 2 )（化学、能源与环境可持续性研究所）；Agency for Science, Technology and Research (A*STAR)（科技研究局）；Institute of Materials Research and Engineering (IMRE)（材料研究与工程研究所）
Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization
1 Department of Computer Science, University of Chicago；2 Data Science \& Learning Division, Argonne National Laboratory；3 Department of Civil, Materials；Environmental Engineering, University of Illinois at Chicago
Generative Discovery of Magnetic Insulators under Competing Physical Constraints
Department of Math, University of Southern California（数学系，南加州大学）；Department of Computer Science, Colby College（计算机科学系，科尔比学院）；California NanoSystems Institute, University of California, Los Angeles（加州大学洛杉矶分校加州纳米系统研究所）
LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking
1 College of Computing \& Data Science (CCDS), Nanyang Technological University (NTU), Singapore 2 Honda Research Institute Europe (HRI-EU), Offenbach am Main, Germany 3 Centre for Frontier AI Research (CFAR), Agency for Science, Technology
