EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents

2026-07-30

AI Summary

This work addresses the limitations of existing life science literature retrieval systems, which are designed for human users and thus hinder AI agents from efficiently obtaining precise evidence due to complex query syntax and the need to process full-text articles. To overcome this, the authors propose the first knowledge layer tailored for AI agents in the life sciences, transforming traditional keyword-based search into an end-to-end natural language question-answering pipeline for evidence retrieval. Leveraging large language models for query planning, the system automatically decomposes questions, invokes the Europe PMC search engine, reads retrieved documents, and pinpoints relevant evidence. Experimental results demonstrate that this approach improves Citation F1 by over 16 points on ScholarQABench and significantly enhances performance on downstream tasks such as fact verification and LitQA2, outperforming general-purpose web search baselines.

Abstract

The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI agents: they take keywords and complex syntax and return whole papers, so every agent must learn the syntax, issue several searches, and read full papers to find the evidence it needs. We introduce EMBL AI Librarian, a knowledge layer that upgrades the Europe PMC interface for AI agents: an agent asks in natural language and receives evidence that answers it. A single LLM orchestrates the whole knowledge retrieval process: it plans complementary subqueries executed by the live Europe PMC search engine, then reads the selected papers and locates the relevant evidence. We evaluate Librarian across four benchmarks: literature synthesis, claim verification, open-domain question answering, and downstream biology tasks such as protocol questions and sequence manipulation. On ScholarQABench, Librarian improves Citation F1 by more than $16$ points over strong recently published baselines. Used as the retrieval layer of an existing claim-verification pipeline, it increases agreement with expert consensus; and on the open-form LitQA2 benchmark, a GPT-5.4 agent scores about $8$ points higher when grounded in Librarian than with web search. Overall, our results show that equipping life-science agents with the Librarian knowledge layer improves performance across a range of tasks. We release our code publicly at https://github.com/petroni-lab/librarian

Problem

• AI agents
• life-sciences
• literature retrieval
• knowledge access
• Europe PMC

Innovation

• AI agent
• knowledge retrieval
• natural language querying
• life sciences
• evidence extraction