Can we automate scientific reasoning in closed-loop experiments using large language models?
Abstract
Reasoning models (LLMs) were used as optimisers for a 10-D chemistry problem and a 7-D physics simulation. The best performance was achieved using iterative closed-loop reasoning with a batch size of one.
Fields of Study & Subjects
Machine Learning in Materials Science
Topic Modeling
Multimodal Machine Learning Applications
Publication details
- Journal / source
- Digital Discovery
- Publisher
- Royal Society of Chemistry (RSC)
- Volume
- 5
- Issue
- 3
- Pages
- 1132–1160
- Publication date
- 1 January 2026
- Language
- EN