本研究探索将大语言模型（large language models, LLMs）融入科学数据同化，以燃烧科学为案例展开研究。研究利用集成了检索增强生成（Retrieval-Augmented Generation, RAG）框架的基础模型，提出了一种处理各类燃烧研究数据的方法，覆盖实验研究、模拟仿真和文献资料三类数据。燃烧研究的多面性凸显了知识处理在从海量多元来源中梳理和提取有价值信息方面的关键作用。所提出的方法在优化数据隐私性与准确性的同时，降低了计算成本与经济开销。该方法融合了提示工程与离线开源LLM，支持用户自主选择基础模型。本研究对文本分割策略进行了全面梳理，开展了不同LLM之间的对比研究，并探索了多种优化后的提示词以验证框架的有效性。通过接入外部数据库，该框架在生成准确回答、构建严谨论证方面的表现优于传统LLM。此外，本研究还深入探究了用于高效提取科学文献信息的优化提示模板。为解决幻觉问题和虚假研究文献问题，本研究设计了定制工作流，搭配检测算法以过滤不准确信息。尽管仍存在可改进之处，该框架能在极少人工监督的情况下持续输出准确的领域专属回答。所提出的与提示无关的方法为后续相关研究提供了可行方向。本研究强调了将LLM与知识处理技术融入科学研究的重要意义，为数据同化与数据利用领域的进展奠定了基础。
英文摘要：
This research explores the integration of large language models (LLMs) into scientific data assimilation, focusing on combustion science as a case study. Leveraging foundational models integrated with Retrieval-Augmented Generation (RAG) framework, the study introduces an approach to process diverse combustion research data, spanning experimental studies, simulations, and literature. The multifaceted nature of combustion research emphasizes the critical role of knowledge processing in navigating and extracting valuable information from a vast and diverse pool of sources. The developed approach minimizes computational and economic expenses while optimizing data privacy and accuracy. It incorporates prompt engineering and offline open-source LLMs, offering user autonomy in selecting base models. The study provides a thorough examination of text segmentation strategies, conducts comparative studies between LLMs, and explores various optimized prompts to demonstrate the effectiveness of the framework. By incorporating an external database, the framework outperforms a conventional LLM in generating accurate responses and constructing robust arguments. Additionally, the study delves into the investigation of optimized prompt templates for the purpose of efficient extraction of scientific literature. The research addresses concerns related to hallucinations and false research articles by introducing a custom workflow developed with a detection algorithm to filter out inaccuracies. Despite identified areas for improvement, the framework consistently delivers accurate domain-specific responses with minimal human oversight. The prompt-agnostic approach introduced holds promise for future deliberations. The study underscores the significance of integrating LLMs and knowledge processing techniques in scientific research, providing a foundation for advancements in data assimilation and utilization.
The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
Singapore Management University（新加坡管理大学）；The Hong Kong Polytechnic University（香港理工大学）；Nanyang Technological University（南洋理工大学）；Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)（信息通信研究院，科技研究局（A*STAR））；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation
The International Joint Institute of Tianjin University, Fuzhou, Tianjin University, China（天津大学福州国际联合学院）；TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China（天津大学计算机科学与技术学院TJUNLP实验室）
Lessons from Neuroscience for AI: How integrating Actions, Compositional Structure and Episodic Memory could enable Safe, Interpretable and Human-Like AI
Physics-Guided Multimodal Transformers are the Necessary Foundation for the Next Generation of Meteorological Science
School of Artificial Intelligence, Beijing University of Posts；Huawei Noah's Ark Lab；Department of Earth System Science, Tsinghua University；College of Computing \& Data Science, Nanyang Technological University；State Key Laboratory of Networking；Switching Technology, Beijing University of Posts
Defining Foundation Models for Computational Science: A Call for Clarity and Rigor
Center for Applied Scientific Computing（应用科学计算中心）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Intelligence and Interaction Research Center（智能交互研究中心）；Korea Institute of Science and Technology（韩国科学技术院）；Department of Mathematics（数学系）；Virginia Tech（弗吉尼亚理工大学）；Quantitative Modeling and Software Engineering（定量建模与软件工程）；Sandia National Laboratories（桑地亚国家实验室）；Department of Aerospace Engineering（航空航天工程系）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Dept. Computational Applied Mathematics and Operations Research（计算应用数学与运筹学系）；Rice University（莱斯大学）
Social Science Is Necessary for Operationalizing Socially Responsible Foundation Models
Siebel School of Computing and Data Science（西贝尔计算与数据科学学院）；The Grainger College of Engineering（格兰杰工程学院）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tübingen AI Center（蒂宾根人工智能中心）；University of Tübingen（蒂宾根大学）；School of Complex Adaptive Systems（复杂适应系统学院）；Arizona State University（亚利桑那州立大学）；School for the Future of Innovation in Society（社会创新未来学院）
Mars-Bench: A Benchmark for Evaluating Foundation Models for Mars Science Tasks
School of Computing and Augmented Intelligence, Arizona State University（计算与增强智能学院，亚利桑那州立大学）；School of Earth and Space Exploration, Arizona State University（地球与空间探索学院，亚利桑那州立大学）；Jet Propulsion Laboratory, California Institute of Technology（喷气推进实验室，加州理工学院）
SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
AI Centre, University College London（伦敦大学学院人工智能中心）；University College London（伦敦大学学院）；Central South University（中南大学）；University of Massachusetts at Amherst（马萨诸塞大学阿姆赫斯特分校）
AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Department of Engineering Science, University of Oxford（牛津大学工程科学系）；Shanghai Institute for Science of Science（上海科学科学研究院）；School of Mathematics, Southeast University（东南大学数学学院）；Shanghai Innovation Institute（上海创新研究院）；Department of Information Engineering, Chinese University of Hong Kong（香港中文大学信息工程系）
BioMap Research（BioMap研究部）；AI Lab, Research Center for Industries of the Future（人工智能实验室，未来产业研究中心）；Westlake University（西湖大学）；University of Chinese Academy of Sciences, China（中国科学院大学）
Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy
College of Mathematical Medicine, Zhejiang Normal University（浙江师范大学数学医学院）；DAIS, Ca’ Foscari University of Venice（威尼斯大学DAIS）；European Centre for Living Technology（欧洲生命技术中心）
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University（吉林大学符号计算与知识工程教育部重点实验室）
Large Knowledge Model: A Knowledge Foundation for Agentic Science at Scale
DP Technology；Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；International Center for Quantum Materials, School of Physics, Peking University（北京大学物理学院量子材料科学中心）；Lanzhou Center for Theoretical Physics, Lanzhou University（兰州大学理论物理研究中心）；AI for Science Institute（AI for Science 研究院）；School of Mathematical Sciences, Peking University（北京大学数学科学学院）；Center for Machine Learning Research, Peking University（北京大学机器学习研究中心）
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
State Key Laboratory of High Performance Ceramics（高性能陶瓷国家重点实验室）；Shanghai Institute of Ceramics, Chinese Academy of Sciences（中国科学院上海陶瓷研究所）；Center of Materials Science and Optoelectronics Engineering, University of Chinese Academy of Sciences（中国科学院大学材料科学与光电子工程中心）；School of Chemistry and Materials Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州先进研究所化学与材料科学学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Beijing Wenge Technology Co., Ltd.（北京文格科技有限公司）；College of Medicine and Biological Information Engineering, Northeastern University（东北大学医学与生物信息工程学院）
Strategic Governance of AI Models in Earth Science
University of Utah（犹他大学）；NASA Goddard Space Flight Center（美国国家航空航天局戈达德太空飞行中心）；University of Bristol（布里斯托大学）；Stanford University（斯坦福大学）；Center for Astrophysics | Harvard & Smithsonian（哈佛-史密森天体物理中心）；GESTAR II, NASA Global Modeling and Assimilation Office（GESTAR II，美国国家航空航天局全球建模与同化办公室）；University of Southern California（南加州大学）；University of Reading（雷丁大学）
Information Science Principles of Machine Learning: A Causal Chain Meta-Framework Based on Formalized Information Mapping
Koguan School of Law, China Institute for Smart Justice, School of Computer Science, Shanghai Jiao Tong University（柯 guar 法学院、中国智能正义研究院、计算机科学学院、上海交通大学）
