Robin: A multi-agent system for automating scientific discovery

2025/05/19 by Ali Essam Ghareeb, Ali Ghareeb, Benjamin Chang +19 · 15 voices · 21 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Medicine · #Computational Drug Discovery Methods #Machine Learning in Bioinformatics #Retinal Imaging and Analysis #cs.AI #cs.MA #q-bio.QM

paper · pdf · doi:10.48550/arxiv.2505.13400

openalex publication_date 2025/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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.

Citations

• Language agents achieve superhuman synthesis of scientific knowledge
• RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS

Cited by

• ASI-Evolve: AI Accelerates AI
• Kosmos: An AI Scientist for Autonomous Discovery
• Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents
• BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
• QMBench: A Research Level Benchmark for Quantum Materials Research
• Bohrium + SciMaster: Building the Infrastructure and Ecosystem for Agentic Science at Scale
• PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
• MemEvolve: Meta-Evolution of Agent Memory Systems
• A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
• Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science
• AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
• Opportunities for artificial intelligence and synthetic biology in designing living drug delivery systems
• Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation
• SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning
• Co-TAP: Three-Layer Agent Interaction Protocol Technical Report
• Physics-Informed Machine Learning in Biomedical Science and Engineering
• MAS²: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
• The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems
• AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
• Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science
• HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research

Discussions

• Robin: A multi-agent system for automating scientific discovery [hn, 151 points, 20 comments]
• I genuinely don't understand why I would need a llm to analyze data and interpret the results from an experimental study. The search/hypothesis generation could indeed be useful with genuine expert ov [bsky, 7 points, 1 comments]
• Robin: A multi-agent system for automating scientific discovery arxiv.org/abs/2505.13400 🧬🖥️🧪 github.com/Future-House... [bsky, 3 points, 0 comments]
• autonomous multi-agent system that fully automates hypothesis generation, experimentation, and analysis arxiv.org/abs/2505.13400 #AI #AgenticAI #AIAgents #GenAI [bsky, 1 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery #HackerNews https://arxiv.org/abs/2505.13400 [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery https://arxiv.org/abs/2505.13400 https://news.ycombinator.com/item?id=44043323 [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery https://arxiv.org/abs/2505.13400 [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery View Article | Join the HN Conversation Summary of HN discussion 🧵👇 #hacker-news [bsky, 0 points, 1 comments]
• ¿Y si una IA pudiera hacer ciencia de principio a fin? Flipas con Robin, un sistema multiagente que busca papers, genera hipótesis, analiza datos y hasta sugiere tratamientos médicos. Ya encontró uno [bsky, 0 points, 0 comments]
• Pre-print paper arxiv.org/abs/2505.13400 [bsky, 0 points, 1 comments]
• https://bsky.app/profile/hackernews.com.web.brid.gy/post/3lpmprrcsiou2 [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery https://arxiv.org/abs/2505.13400 (https://news.ycombinator.com/item?id=44043323) [bsky, 0 points, 0 comments]
• arxiv.org/abs/2505.13400 Futurehouse's new agentic platform proposes boosting RPE phagocytosis as a potential treatment for atrophic AMD. We'd like to avoid repeat injections of a drug so a vector tha [bsky, 0 points, 0 comments]
• Robin: A multi-agent system for automating scientific discovery https://arxiv.org/abs/2505.13400 (https://news.ycombinator.com/item?id=44043323) [bsky, 0 points, 0 comments]

Related

• Accelerating scientific discovery with Co-Scientist
• Can AI Agents Design and Implement Drug Discovery Pipelines?
• AI Agents in Drug Discovery
• Collaborative Intelligence in Sequential Experiments: A Human-in-the-Loop Framework for Drug Discovery
• Biomni: A General-Purpose Biomedical AI Agent