Tag
The paper introduces EMBL AI Librarian, a knowledge layer that lets life-science AI agents query Europe PMC using natural language and receive direct evidence. It improves retrieval and downstream task performance across multiple benchmarks, with code released publicly.
PaSaMaster is a self-evolving agentic literature retrieval system that iteratively refines search intent and produces evidence-grounded paper rankings, outperforming GPT-5.2 by 30% at 1% cost with zero hallucinations.