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

2025-07-02

AI Summary

Current biological experimentation automation faces critical bottlenecks, including poor adaptability of large language models (LLMs) and vision-language models (VLMs), limited fault tolerance, and operational complexity. To address these challenges, this work introduces the first autonomous experimental platform integrating LLMs, VLMs, and a modular robotic system, implemented via a hierarchical multi-agent architecture comprising biologist, technician, and inspector agents. The platform enables dynamic experimental design, context-aware optimization, and real-time anomaly detection. Technically, it incorporates retrieval-augmented generation, multimodal perception, robot-oriented pseudocode generation, and a lightweight anomaly identification algorithm, supported by modular hardware and a human-in-the-loop web interface. Evaluated on retinal pigment epithelium organoid differentiation, the system achieves or exceeds human performance in cell viability, morphological integrity, and batch consistency—demonstrating robustness and generalizability in real-world laboratory settings.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Overcoming rigid protocol design in autonomous biological experiments
• Enhancing adaptability to dynamic lab conditions and error handling
• Reducing operational complexity in AI-driven laboratory automation

Innovation

• Hierarchical multi-agent architecture for autonomy
• Retrieval-augmented protocol generation and execution
• Multimodal perception for real-time anomaly detection