ThinkFactory 2025: Community Discussion on Harmonizing and Accelerating Self-Driving Laboratories

21 December 2025, Version 1
This content is an early or alternative research output and has not been peer-reviewed by Cambridge University Press at the time of posting.

Abstract

ThinkFactory 2025 was a virtual workshop jointly hosted by the Acceleration Consortium and CMAC to facilitate discussion on harmonizing and accelerating self-driving laboratories. The three-hour event brought together more than 50 participants for plenary and breakout discussion across four themed tracks: AI and machine learning, data, orchestration, and robotics. Key priorities highlighted by the community included the need for clearer benchmarks to demonstrate value, improved accessibility for experimentalists without programming expertise, and stronger standards for interoperability, safety, and reproducibility. Participants also emphasised the importance of structured human–AI collaboration and shared infrastructure to promote openness and efficiency. This paper outlines the event structure and design and key discussion insights, providing a reproducible framework for hosting collaborative, cross-institutional virtual workshops.

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting and Discussion Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.