Mohammed Saqlain · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29812 · open-access PDF
Agen bahasa pencarian sastra menjadi komponen standar asisten ilmiah untuk ilmu kehidupan, namun ada sedikit bukti terkontrol tentang bagian mana dari pelindung mereka yang penting. Kami menjalankan ablasi terkontrol pada verifikasi klaim biomedis (SciFact) dengan Live PubMed API sebagai satu-satunya alat. Memegang tulang belakang dan format output tetap, kami membandingkan empat pelindung: jawaban buku tertutup, pencarian satu kali menggunakan klaim sebagai kueri, agen gaya ReAct yang menulis pertanyaan PubMed sendiri, dan oracle yang diberikan abstrak emas, masing-masing dengan dua tulang belakang perbatasan yang efisien
Machine translation (Meta M2M100); the English original follows.
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 in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29812, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange