# Real-time experiment-theory closed-loop interaction for autonomous materials science

arXiv: https://arxiv.org/abs/2410.17430 · HTML: https://mlsanity.com/paper/2410.17430/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 83 references that are in the map.
- First posted on arXiv 22 Oct 2024.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Gaussian Processes for Big Data](https://mlsanity.com/paper/1309.6835/) (2013)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [GPflow: A Gaussian process library using TensorFlow](https://mlsanity.com/paper/1610.08733/) (2016)
- [Bayesian Optimization for Materials Design with Mixed Quantitative and Qualitative Variables](https://mlsanity.com/paper/1910.01688/) (2019)
- [Autonomous synthesis of metastable materials](https://mlsanity.com/paper/2101.07385/) (2021)
- [BraggNN: Fast X-ray Bragg Peak Analysis Using Deep Learning](https://mlsanity.com/paper/2008.08198/) (2020)
- [Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning](https://mlsanity.com/paper/2108.09523/) (2021)
- [Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering](https://mlsanity.com/paper/1802.07307/) (2018)
- [aflow.org: A Web Ecosystem of Databases, Software and Tools](https://mlsanity.com/paper/2207.09842/) (2022)

## Built on by (most cited first, 3 of 3)

- [Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery](https://mlsanity.com/paper/2605.04375/) (2026)
- [Real-time Multi-instrument Autonomous Discovery of Novel Phase-change Memory Materials](https://mlsanity.com/paper/2605.18033/) (2026)
- [Agentic self-driving microscopy benchmarks support qualification but do not necessarily generalize to unseen tasks](https://mlsanity.com/paper/2608.05266/) (2026)

## Abstract (arXiv)

Iterative cycles of theoretical prediction and experimental validation are the cornerstone of the modern scientific method. However, the proverbial "closing of the loop" in experiment-theory cycles in practice are usually ad hoc, often inherently difficult, or impractical to repeat on a systematic basis, beset by the scale or the time constraint of computation or the phenomena under study. Here, we demonstrate Autonomous MAterials Search Engine (AMASE), where we enlist robot science to perform self-driving continuous cyclical interaction of experiments and computational predictions for materials exploration. In particular, we have applied the AMASE formalism to the rapid mapping of a temperature-composition phase diagram, a fundamental task for the search and discovery of new materials. Thermal processing and experimental determination of compositional phase boundaries in thin films are autonomously interspersed with real-time updating of the phase diagram prediction through the minimization of Gibbs free energies. AMASE was able to accurately determine the eutectic phase diagram of the Sn-Bi binary thin-film system on the fly from a self-guided campaign covering just a small fraction of the entire composition - temperature phase space, translating to a 6-fold reduction in the number of necessary experiments. This study demonstrates for the first time the possibility of real-time, autonomous, and iterative interactions of experiments and theory carried out without any human intervention.