Adaptive Human-in-the-Loop Optimization Using Language-Guided Priors for Chemical Synthesis

Amirreza Mottafegh, Gwang-Noh Ahn

Submission Type: I want my submission to be considered for both oral and poster presentation.

Keywords: Bayesian Optimization, Human-in-the-Loop, Large Language Models, Self-Driving Laboratories, Chemical Synthesis, Adaptive Priors, Autonomous Experimentation

TL;DR: We accelerate autonomous chemical discovery by using LLMs to translate expert language into optimization priors, while employing a safety guard mechanism that automatically disables the prior if the data proves the expert wrong.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 102