BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments

TL;DR

BioMARS is an AI-driven robotic platform that autonomously designs, plans, and executes biological experiments, demonstrating high performance and adaptability in lab tasks through integrated language models and modular robotics.

Contribution

Introduction of BioMARS, a hierarchical multi-agent system combining LLMs, VLMs, and robotics for autonomous biological experimentation with real-time human collaboration.

Findings

BioMARS autonomously conducts cell passaging with high viability.

System outperforms traditional methods in cell differentiation tasks.

Achieves scalable, adaptable lab automation with real-time monitoring.

Abstract

Large language models (LLMs) and vision-language models (VLMs) have the potential to transform biological research by enabling autonomous experimentation. Yet, their application remains constrained by rigid protocol design, limited adaptability to dynamic lab conditions, inadequate error handling, and high operational complexity. Here we introduce BioMARS (Biological Multi-Agent Robotic System), an intelligent platform that integrates LLMs, VLMs, and modular robotics to autonomously design, plan, and execute biological experiments. BioMARS uses a hierarchical architecture: the Biologist Agent synthesizes protocols via retrieval-augmented generation; the Technician Agent translates them into executable robotic pseudo-code; and the Inspector Agent ensures procedural integrity through multimodal perception and anomaly detection. The system autonomously conducts cell passaging and culture tasks, matching or exceeding manual performance in viability, consistency, and morphological integrity. It also supports context-aware optimization, outperforming conventional strategies in differentiating retinal pigment epithelial cells. A web interface enables real-time human-AI collaboration, while a modular backend allows scalable integration with laboratory hardware. These results highlight the feasibility of generalizable, AI-driven laboratory automation and the transformative role of language-based reasoning in biological research.