HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience

• URL: http://arxiv.org/abs/2608.14055v1
• Date: Fri, 14 Aug 2026 07:59:58 GMT
• Title: HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience
• Abstract summary: HERMES is a scalable multi-agent framework that extracts structured data from scientific documents.<n>It integrates domain constraints, validation rules and evidence tracing within a unified document-level extraction process.<n>The system produced a structured database of 32,277 fossil entities and 451,878 attributes, released online at https://treatise.geolex.org.
• Score: 41.77130029890288
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent [55.77954024801206]
  Marine lead (Pb) and its isotopes are critical tracers for ocean circulation and anthropogenic pollution.<n>Manual extraction is unscalable, while general-purpose Large Language Models (LLMs) lack the necessary domain-specific knowledge.<n>We introduce an expert-guided adaptation approach that enables LLMs to perform rigorous scientific data extraction without fine-tuning.
  arXiv  Detail & Related papers  (2026-05-28T14:06:25Z)
• Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System [4.222675210976564]
  Polymer literature contains a large and growing body of experimental knowledge.<n>Much of it is buried in unstructured text and inconsistent terminology.<n>Existing tools typically extract narrow, study-specific facts in isolation.
  arXiv  Detail & Related papers  (2026-02-18T17:46:09Z)
• MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables [19.837905352477453]
  MatSKRAFT is a framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale.<n>MatSKRAFT significantly outperforms state-of-the-art large language models, achieving F1 scores of 88.68 for property extraction and 71.35 for composition extraction.
  arXiv  Detail & Related papers  (2025-09-12T17:55:11Z)
• A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers [251.23085679210206]
  Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research.<n>This survey reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate.<n>We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge.
  arXiv  Detail & Related papers  (2025-08-28T18:30:52Z)
• An Effective Approach for Node Classification in Textual Graphs [0.5062312533373298]
  We propose a novel framework that integrates TAPE (Text-Attributed Graph Representation Enhancement) with Graphormer.<n>Our approach generates semantically rich explanations from paper content, which are then fused into enhanced node representations.<n>We demonstrate the efficacy of our framework on the challenging ogbn-arxiv dataset, achieving state-of-the-art performance with a classification accuracy of 0.772.
  arXiv  Detail & Related papers  (2025-08-07T20:24:00Z)
• HySemRAG: A Hybrid Semantic Retrieval-Augmented Generation Framework for Automated Literature Synthesis and Methodological Gap Analysis [55.2480439325792]
  HySemRAG is a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG)<n>System addresses limitations in existing RAG architectures through a multi-layered approach.
  arXiv  Detail & Related papers  (2025-08-01T20:30:42Z)
• SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents [49.54155332262579]
  We release a new entity and relation extraction dataset for entities related to datasets, methods, and tasks in scientific articles. Our dataset contains 106 manually annotated full-text scientific publications with over 24k entities and 12k relations.
  arXiv  Detail & Related papers  (2024-10-28T15:56:49Z)
• SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [97.31347312130119]
  SciRIFF (Scientific Resource for Instruction-Following and Finetuning) is a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks.<n>These tasks span five core scientific literature understanding capabilities: information extraction, summarization, question answering, claim verification, and classification.<n> SciRIFF is unique in being entirely expert-written, high-quality instruction-following dataset for extracting and synthesizing information from research literature across diverse scientific fields.
  arXiv  Detail & Related papers  (2024-06-10T21:22:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.