{
  "abstract": "Large language models are increasingly used to guide sequential biological screens, yet standard evaluations rely on raw hit counts that conflate a proposer's value with the discovery capacity of the underlying algorithmic harness. Adaptive sampling and corrupted experimental readouts also leave standard feedback comparisons without a false-discovery guarantee. We present Certified Agentic Discovery Screens (CADS), an error-controlled measurement framework that quantifies a proposer's incremental value against an identical LLM-free loop. By integrating capped likelihood-ratio bounds, e-processes, and complete-family e-BH, CADS controls the terminal false discovery rate under the stated null and corruption conditions despite arbitrary dependence, adaptive sampling, and optional stopping. In DepMap-backed simulations, CADS exposes two evaluation artifacts: the LLM-free harness alone clears the feedback gate, and raw origin counts overstate LLM contributions because LLM picks displace fallback discoveries. On the initial 20 seeds, supplying tested-candidate history to Qwen2.5-7B shifts its net contribution from +0.35, with a 95% interval covering zero, to +2.90, with the interval above zero. This initial net effect did not persist in a 50-seed matched-quota replication. These results support net gain over an LLM-free loop, measured between separately certified sets, as the appropriate measure of proposer contribution.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.24597",
  "author_total": 6,
  "authors": [
    {
      "name": "Guanxing Chen"
    },
    {
      "name": "Nihui Shao"
    },
    {
      "name": "Haohuai He"
    },
    {
      "name": "Zhenchao Tang"
    },
    {
      "name": "Pengwei Hu"
    },
    {
      "name": "Zhi-An Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/c4e5e7p7frn5h.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.24597",
  "fulltext_url": null,
  "id": "c4e5e7p7frn5h",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.24597",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7223047550",
  "pdf_url": "https://arxiv.org/pdf/2610.24597",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/c4e5e7p7frn5h.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:31:01Z",
      "native_id": "2610.24597",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.24597"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "CADS: Measuring the Incremental Contribution of LLM Proposers in Sequential Biological Screens",
  "title_text": "CADS: Measuring the Incremental Contribution of LLM Proposers in Sequential Biological Screens",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:50Z",
  "url": "https://research.draconitic.com/paper/c4e5e7p7frn5h",
  "venue": "arXiv",
  "versions": []
}