cs.RONov 8, 2026

A Physical Testbed for Self-Driving Laboratories: Comparing Bayesian and Agentic Optimization in a Minimal Closed-Loop Color Formulation Task

Authors: Tony Qin, Ziheng Wu, Maximilian Schommer, Roya Amini-Naieni, Aldair Gongora

Organizations: Department of Computer Science, The University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, 27599, USA · Lawrence Livermore National Laboratory, Livermore, California, 94550, USA · Trilobio, San Francisco, California, 94107, USA

Abstract

Self-driving laboratories (SDLs) integrate laboratory robotics and automation with AI-driven decision-making to close the design-build-test-learn (DBTL) cycle. However, physical testbeds that combine off-the-shelf hardware and AI into a functioning closed-loop workflow remain in early stages of development, and their integration with commercial laboratory automation is comparatively less developed. In this work, we develop a physical testbed that assembles and integrates commercially available laboratory automation instruments and demonstrate continuous, closed-loop, autonomous operation over 24 cumulative hours of unattended experimentation. We validate this platform on a minimal closed-loop discovery task in which the system autonomously formulates aqueous dye mixtures to match a target absorbance spectrum. The system completed six independent campaigns, each consisting of 48 closed-loop iterations over approximately four hours. In every campaign, the system autonomously selected, dispensed, and measured each mixture, with an AI-driven decision-making algorithm determining subsequent formulations without human intervention. Using this testbed, we compared the performance of two AI-driven decision-making algorithms, traditional Bayesian optimization (BO) and an agentic approach, in selecting mixtures under a fixed total-volume constraint. The agentic optimizer matched target absorbance spectra using fewer iterations than BO, with reductions up to 52%, and converged on a solution for one target that BO failed to match within 48 iterations. These results demonstrate a reference physical platform for SDLs that can evaluate both established and emerging AI strategies, including large language model (LLM)-directed optimization, before their deployment in real-world applications where experiments may be costly and time-consuming to prepare.

Figures & tables

Explore similar work

CardsList
  1. La Agente Óptima: Towards Agentic Self-Driving Laboratories

    Sep 3, 2026Marcel Müller, Jiaru Bai, Willi Gottstein +14self-driving laboratoriesBayesian Optimization

  2. Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery

    Jul 5, 2026Kyunghoon Hur, Chihun LeeAI for Scienceself-driving laboratories

  3. Self-Building Labs

    Oct 16, 2026Jiaru Bai, Yuchi Zhao, Yang Cao +10Laboratory AutomationRobotic Laboratory Automation