BioMARS 2.0: a robotic biologist for formulating and adapting biological experiments
BioMARS 2.0: a robotic biologist for formulating and adapting biological experiments
This paper introduces BioMARS 2.0, a human-in-the-loop multi-agent robotic system designed to automate biological experimentation by connecting knowledge-guided decision-making with robotic execution and biological feedback. The system generates literature-grounded protocols, adapts culture conditions based on image-derived phenotypes from retinal organoid cultures, and nominates drug-repurposing candidates for wet-lab testing. Studies demonstrate improvements in expert-reviewed protocol quality scores across four model backends and higher reported scores in later rounds of a three-round experiment, showcasing feedback-driven robotic biological experimentation.
The system integrates knowledge-guided decision-making with robotic execution to adapt culture conditions and select interventions based on biological feedback, though the abstract does not specify exact performance metrics or deployment readiness.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Shared controlOpen source S3
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ine which experiments should be performed next or how they should change in response to biological feedback. Here we introduce BioMARS, a human-in-the-loop multi-agent robotic system that connects knowledge-guided experimental decision-making with robotic execution and biological feedback. At the procedural level, BioMARS generated literature-grounded protocols and traceable action plans, improving expert-reviewed pr
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org