AI 中文总结
该研究提出HERMES多智能体框架，可从地球科学超长文档中提取结构化知识，在《无脊椎古生物学论著》上的实验显示其性能稳定、效率高且跨领域迁移性好，为历史文献结构化提供了可行途径。
AI 中文摘要
地球科学领域的权威科学知识大多仍被困在传统专著和历史文献中，其中非结构化文本和复杂布局阻碍了计算访问。我们提出HERMES，这是一个可扩展的多智能体框架，用于从超长科学文档中提取结构化数据。利用一个协调大型语言模型，HERMES在统一的文档级提取过程中整合了领域约束、验证规则和证据追踪，该过程包含解析后的文本、表格、图表和图注。将其应用于55卷的《无脊椎古生物学论著》，该系统生成了包含32277个化石分类实体和451878个属性的结构化数据库，已在线发布于指定网址。提取性能在不同化石类群中保持稳定，实体的平均F1分数约为0.90，属性的平均F1分数约为0.91，相对于测试的完全人工基线，每卷效率提高了约6倍。在未进行额外模型训练的情况下，对古地磁学和地球化学的评估证明了其在不同地球科学领域的迁移能力。这项工作为将历史科学文献转化为面向FAIR的结构化数据提供了可行途径，为数据密集型学科和大规模知识整合提供了可持续的基础设施。
英文摘要
Authoritative scientific knowledge in geoscience remains largely trapped in legacy monographs and historical literature, where unstructured text and complex layouts hinder computational access. We introduce HERMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents. Using a coordinating large language model, HERMES integrates domain constraints, validation rules and evidence tracing within a unified document-level extraction process that incorporates parsed text, tables, figures and captions. Applied to the 55-volume Treatise on Invertebrate Paleontology, the system produced a structured database of 32,277 fossil taxonomic entities and 451,878 attributes, released online at https://treatise.geolex.org. Extraction performance remained stable across fossil groups (average F1 scores of approximately 0.90 for entities and 0.91 for attributes), improving per-volume efficiency approximately sixfold relative to the tested fully manual baseline. Evaluation in palaeomagnetism and geochemistry, conducted without additional model training, demonstrated transfer across distinct geoscience domains. This work provides a practical pathway to transform historical scientific literature into FAIR-oriented structured data, offering a sustainable infrastructure for data-intensive disciplines and large-scale knowledge integration.
Comments31-page main manuscript with 6 figures and 3 tables; supplementary information included
