Robin: A multi-agent system for automating scientific discovery

2025-05-19

AI Summary

This study addresses the fragmentation bottleneck in scientific discovery—namely, the disconnection among background literature review, hypothesis generation, experimental design, and data analysis. We propose the first end-to-end multi-agent system for automated scientific discovery, integrating retrieval-augmented large language models, biomedical knowledge graphs, automated experimental protocol generation, RNA-seq analysis pipelines, and multi-agent negotiation mechanisms. Applied to age-related macular degeneration (AMD) research, the system autonomously completed a closed-loop AI-driven workflow: hypothesis generation → wet-lab validation → mechanistic interpretation. It identified ripasudil (a ROCK inhibitor) as a novel enhancer of retinal pigment epithelium phagocytic function, validated its repurposing potential for AMD, and uncovered ABCA1 as the key molecular target. All core figures and conclusions were generated autonomously by the system, markedly enhancing research autonomy and efficiency.

Technology Category

• Multiagent Systems: Mechanism Design
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Scientific discovery is driven by the iterative process of background research, hypothesis generation, experimentation, and data analysis. Despite recent advancements in applying artificial intelligence to scientific discovery, no system has yet automated all of these stages in a single workflow. Here, we introduce Robin, the first multi-agent system capable of fully automating the key intellectual steps of the scientific process. 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 a novel treatment for dry age-related macular degeneration (dAMD), the major cause of blindness in the developed world. Robin proposed enhancing retinal pigment epithelium phagocytosis as a therapeutic strategy, and identified and validated a promising therapeutic candidate, ripasudil. 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 critical lipid efflux pump and possible novel target. All hypotheses, experimental plans, 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 a novel therapeutic candidate within an iterative lab-in-the-loop framework, Robin establishes a new paradigm for AI-driven scientific discovery.

Problem

• Automating all stages of scientific discovery in a single workflow
• Identifying novel treatments for diseases like age-related macular degeneration
• Validating therapeutic candidates through autonomous hypothesis generation and experimentation

Innovation

• Multi-agent system automates scientific discovery workflow
• Integrates literature search with data analysis agents
• Autonomous hypothesis generation and experimental validation