A multi-agent system for automating scientific discovery
Мультиагентная система для автоматизации научных открытий
2026-05-19
SCID: 54.1/4uyayhjs
Discuss with AI
RNA-seqdry age-related macular degenerationhypothesis generationmulti-agent systemscientific discovery
Figures from the paper
Abstract (AI)
Scientific discovery is driven by the iterative process of observation, hypothesis generation, experimentation, and data analysis. Despite recent advancements in applying artificial intelligence to biology, no system has yet automated all these stages [1, 2, 3]. Here, we introduce Robin, the first multi-agent system capable of fully automating both hypothesis generation and data analysis for experimental biology. By integrating literature search agents with data analysis agents, Robin can generate hypotheses, propose experiments, interpret experimental results, and generate updated hypotheses, achieving a semi-autonomous approach to scientific discovery. By applying this system, we were able to identify promising therapeutic candidates for dry age-related macular degeneration (dAMD), the major cause of blindness in the developed world [4, 5]. Robin proposed enhancing retinal pigment epithelium phagocytosis as a therapeutic strategy, and identified and confirmed in vitro efficacy for ripasudil and KL001. Ripasudil is a clinically-used Rho kinase (ROCK) inhibitor that has never previously been proposed for treating dAMD. To elucidate the mechanism of ripasudil-induced upregulation of phagocytosis, Robin then proposed and analyzed a follow-up RNA-seq experiment, which revealed upregulation of ABCA1 , a lipid efflux pump and possible novel target. All hypotheses, experimental directions, data analyses, and data figures in the main text of this report were produced by Robin. As the first AI system to autonomously discover and validate novel therapeutic candidates within an iterative lab-in-the-loop framework, Robin establishes a new paradigm for AI-driven scientific discovery.
Key Findings
1
A follow-up RNA-seq analysis proposed by Robin showed upregulation of ABCA1 after ripasudil treatment, suggesting a possible mechanistic target.
2
By integrating literature-search and data-analysis agents, Robin iteratively generates hypotheses, proposes experiments, interprets results, and updates hypotheses in a lab-in-the-loop framework.
3
Robin identified and experimentally confirmed in vitro efficacy of ripasudil and KL001 as promising therapeutic candidates for dry age-related macular degeneration.
4
Robin identified enhancement of retinal pigment epithelium phagocytosis as a therapeutic strategy for dry age-related macular degeneration.
5
Robin is presented as the first multi-agent system to automate hypothesis generation and data analysis for experimental biology.
Research Object
Robin, a multi-agent system applied to experimental biology and therapeutic discovery for dry age-related macular degeneration
Research Subject
Fully automated, iterative generation and validation of therapeutic hypotheses through literature search, experiment proposal, experimental data analysis, and mechanism elucidation
Publication Details
Publication Date
2026-05-19
Journal
Publisher
ISSN
Cited by
297
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Moderated estimation of fold change and dispersion for RNA-seq data with DESeq22014
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery2024
Autonomous chemical research with large language models2023
Accelerating scientific discovery with Co-Scientist2026
Towards end-to-end automation of AI research2026