arXiv cs.CLPaper
HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geoscience
This demonstrates a practical win: LLMs plus agents can actually process long, visually complex documents and produce consistent, verifiable structured output at scale. The F1 scores around 0.90 are solid. If you're building document extraction for scientific literature or similar unstructured archives, this framework is worth studying. The public Treatise database is a real deliverable.