HEMES, a scalable multi-agent framework that extracts structured data from ultra-long scientific documents, is introduced, offering a sustainable infrastructure for data-intensive disciplines and large-scale knowledge integration.
Abstract
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.
The findings suggest that AI-based structured extraction may redefine how organisations formalise expertise, shifting from document-centric storage toward schema-driven knowledge architectures.
Dilyan Georgiev, E. Gourova· European Conference on Knowl...· 0 citations
BizSage is presented, a multi-agent framework combining corpus-level fine-grained retrieval with quality-driven self-evolution that paves the way for reliable research assistance in economics, business, and the broader social sciences.
Yu-He Wu, Guang-Yu Wang, Jia-Xin Liu et al.· 0 citations
The Semantic Tree Advanced module is presented, a specialized hierarchical navigation component for the ResearchSpace platform addressing performance and usability limitations in browsing RDF knowledge graphs.
Remo Grillo, Lucia Giagnolini, P. Bonora· 0 citations
Eolas, a modular pipeline that uses large language models to automatically transform scientific documents into knowledge graphs aligned with a specified ontology, is introduced and demonstrated effectiveness in extracting useful information for scientists studying materials designed to endure the extreme temperatures a...
M. Sbodio, Marcos Martínez Galindo, Vanessa López et al.· 0 citations
Before tool-using LLM agents are deployed in environmental and geospatial workflows, teams need evidence that an agent reliably selects the right operations against real APIs. We introduce GeoNatureAgent (GNA), a framework for pre-production evaluation of tool-using agents: a fixed sixteen-tool geospatial interface pub...
Gabriel Díaz-Ireland, D. Prieto-Herráez, Mario García Peces et al.· 0 citations
Combining large language models (LLMs) with structured knowledge graphs can be a potential way of addressing issues with reliability and explainability of question answering systems in particular domains. While LLMs have been shown to be effective at natural language understanding, they may still hallucinate or fail to...
S. Solanki, Bhupendra Kumar· 2026 International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.