BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909672272822272 |
|---|---|
| author | Qiu, Yibo Huang, Zan Wang, Zhiyu Liu, Handi Qiao, Yiling Hu, Yifeng Sun, Shu'ang Peng, Hangke Xu, Ronald X Sun, Mingzhai |
| author_facet | Qiu, Yibo Huang, Zan Wang, Zhiyu Liu, Handi Qiao, Yiling Hu, Yifeng Sun, Shu'ang Peng, Hangke Xu, Ronald X Sun, Mingzhai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01485 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments Qiu, Yibo Huang, Zan Wang, Zhiyu Liu, Handi Qiao, Yiling Hu, Yifeng Sun, Shu'ang Peng, Hangke Xu, Ronald X Sun, Mingzhai Robotics Artificial Intelligence Multiagent Systems Quantitative Methods 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. |
| title | BioMARS: A Multi-Agent Robotic System for Autonomous Biological Experiments |
| topic | Robotics Artificial Intelligence Multiagent Systems Quantitative Methods |
| url | https://arxiv.org/abs/2507.01485 |