Tag
This paper presents a two-step method for optimizing resource utilization in autonomous laboratories using constraint programming for scheduling and status dependencies for robust execution, demonstrated on a platform for metal-organic framework synthesis.
LabGuard introduces a framework that translates natural-language laboratory safety rules into executable runtime monitors for embodied agents, achieving a reduction in unsafe events from 39.5% to 23.8% while maintaining task success.
LabVLA is a vision-language-action model for scientific laboratory automation, trained with a two-stage approach combining action token pretraining and flow matching. It achieves state-of-the-art success rates on the LabUtopia benchmark by leveraging simulated data to bridge the gap between household demonstrations and lab-specific tasks.