EMBL AI 館員：AI 代理的生命科學知識層

摘要

網路日益由AI代理而非人類所存取。每個代理都需要知識，尤其是在生命科學領域，該領域的代理式管線正快速成長。取得文獻是滿足此需求的關鍵環節，而像Europe PMC這類擁有超過4000萬筆索引記錄的資源，被廣泛用於滿足這項需求。然而，這些資源並非為AI代理而建：它們接受關鍵字和複雜語法，並回傳完整論文，因此每個代理都必須學習其語法、執行多次搜尋，並閱讀全文論文才能找到所需的證據。我們推出EMBL AI Librarian，這是一個知識層，將Europe PMC介面升級為適用於AI代理：代理以自然語言提問，並接收能回答問題的證據。單一大型語言模型（LLM）協調整個知識檢索流程：它規劃由即時Europe PMC搜尋引擎執行的互補性子查詢，然後閱讀所選論文並定位相關證據。我們在四個基準上評估Librarian：文獻綜合、主張驗證、開放領域問答，以及下游生物學任務，例如實驗流程問題和序列操作。在ScholarQABench上，Librarian比近期發表的強力基準高出逾16個百分點的引用F1分數。作為現有主張驗證管線的檢索層使用時，它提高了與專家共識的一致性；而在開放式LitQA2基準上，GPT-5.4代理在以Librarian為基礎時，比使用網路搜尋高出約8個百分點。整體而言，我們的結果顯示，為生命科學代理配備Librarian知識層可提升一系列任務的表現。我們在 https://github.com/petroni-lab/librarian 公開發布我們的程式碼。

English

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