Newest papers

CADS: Measuring the Incremental Contribution of LLM Proposers in Sequential Biological Screens

Guanxing Chen, Nihui Shao, Haohuai He, Zhenchao Tang, Pengwei Hu, Zhi-An Huang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.24597 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Model interval bahasa yang sesuai semakin banyak digunakan untuk membimbing layar biologis berturut-turut, namun evaluasi standar bergantung pada hit-hit mentah yang membingungkan nilai propositor dengan kapasitas penemuan loop algoritmik yang mendasarinya. Sampel adaptif dan pembacaan eksperimental yang rusak juga meninggalkan perbandingan umpan balik standar tanpa jaminan penemuan palsu. Kami menyajikan Certified Agentic Discovery Screens (CADS), kerangka pengukuran yang dikendalikan oleh kesalahan yang mengukur kapasitas penemuan propositor terhadap loop bebas LLM yang identik. Dengan mengintegrasikan batas rasio probabilitas yang tertutup, e-processes, dan e-BH keluarga lengkap, CADS mengontrol tingkat penemuan palsu terminal di bawah status nol dan kondisi korupsi yang disertifikasi meskipun ketergantungan arbitrase, sampel adaptif, dan um

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Measure (data warehouse), Interval (graph theory), Value (mathematics), Conflation, Certification

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange