Awesome Auto Research Hub Papers · Datasets · Projects
← Back to papers

Robin: A multi-agent system for automating scientific discovery

arXiv 2025 68.1 method

TLDR

Robin is a multi-agent system that fully automates scientific discovery, identifying a novel treatment for dry AMD.

Reasoning

The paper presents a novel multi-agent system that integrates literature search and data analysis to automate the entire scientific process, with a real-world application to dry AMD. Strengths include a clear demonstration of end-to-end automation and validation; weaknesses may include limited generalizability and potential overclaim of 'first' without broader comparison.

Read-first score

Read-first score 68.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 96.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Topical relevance 42%
80

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Methodology quality 25%
80

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=analysis,experiment,result,validation

Reproducibility 25%
30

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

FrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 73.

Keyword Scores

automated scientific discovery
10
scientific discovery agent
10
AI scientist
9
automated research
9
AI for scientific research
9
research automation
9
autonomous research agent
8
literature review agent
8
automated experimentation
8
paper writing agent
8
experiment design agent
7
survey generation
1

Deep Analysis

Innovations

  • First multi-agent system to fully automate the iterative scientific discovery process, integrating literature search and data analysis agents to generate hypotheses, design experiments, interpret results, and update hypotheses.
  • Discovery and experimental validation of ripasudil, a clinically-used ROCK inhibitor never previously proposed for treating dry age-related macular degeneration (dAMD).
  • Elucidation of a potential mechanism through RNA-seq analysis, revealing upregulation of ABCA1 as a novel target.

Methodology

Robin is a multi-agent system that combines literature search agents with data analysis agents to perform hypothesis generation, experimental design, result interpretation, and iterative hypothesis refinement in a semi-autonomous lab-in-the-loop framework.

Key Results

Robin identified ripasudil as a novel therapeutic candidate for dAMD by enhancing retinal pigment epithelium phagocytosis, validated it experimentally, and proposed a follow-up RNA-seq experiment that revealed ABCA1 upregulation as a possible mechanism.

Tags

AIMAQM