An Autonomous Agent for Soft Material Structural Optimization and Discovery

Published

June 6, 2025

Author(s)

Tyler Martin, Austin McDannald, Aaron Kusne, Peter Beaucage

Abstract

The pace of formulation (re)development and design is rapidly increasing as both consumers and new legislation demand products that do less harm to the environment while maintaining high standards of performance. To meet this need, we have developed an autonomous platform called the Autonomous Formulation Lab (AFL) that can automatically prepare and measure the microstructure of liquid formulations using small-angle neutron and X-ray scattering and, soon, a variety of other techniques. Here, we describe the design, philosophy, tuning, and validation of our active learning agent that guides the course of AFL experiments. We show how our extensive in-silico tuning results in an agent that is efficient and robust to both the number of measurements and signal to noise variation. Finally, we experimentally demonstrate our virtually tuned agent on a model formulation problem of replacing a petrol-derived formulation component with a natural analog. We show that the agent efficiently maps both formulations and how post-hoc analysis of the measured data reveals the opportunity for further specialization of the agent. With the tuned and proven active learning agent, our autonomously guided AFL platform will accelerate the pace of discovery of liquid formulations and help speed us towards a greener future.

Citation

(potentially a different journal, still TBD)

Volume

37

Issue

12

Pub Type

Journals

Download Paper

https://doi.org/10.1021/acs.chemmater.5c00860

Local Download

Citation

Martin, T. , McDannald, A. , Kusne, A. and Beaucage, P. (2025), An Autonomous Agent for Soft Material Structural Optimization and Discovery, (potentially a different journal, still TBD), [online], https://doi.org/10.1021/acs.chemmater.5c00860, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=956694 (Accessed October 20, 2025)