SOURCE-LINKED INTELLIGENCE

Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents

arXiv · AI, language, vision and robotics · article · Oct 21, 2026 · UTC

Literature-searching language agents are becoming a standard component of scientific assistants for the life sciences, yet there is little controlled evidence on which parts of their harness matter. We run a controlled ablation on biomedical claim verification (SciFact) with the live PubMed API as the only tool. Holding the backbone and output format fixed, we compare four harnesses: closed-book answering, single-shot retrieval using the claim as the query, a ReAct-style agent that writes its own PubMed queries, and an oracle given the gold abstracts, each with two efficient frontier backbones

Read original source ↗ Open in workspace

recordType

paper

region

Global