Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis
Abstract
Autonomous experimentation offers a time-efficient route towards accelerated catalyst discovery, but current practices often rely on black-box models that are difficult to interpret. Here we demonstrate the paradigm of interpretable autonomous exploration of a 12-dimensional space in the electrocatalytic hydrogen evolution reaction by integrating an interpretable decision-making artificial intelligence with a fully automated electrochemical platform. Guided by a human’s chemistry-informed hypothesis, a chemistry-infused bandit is established to reflect the locally quadratic approximation between synthetic conditions and electrocatalytic activities near the explored optimum region. Not only does such a decision-making bandit lead to the discovery of previously unreported, earth-abundant electrocatalysts at least comparable to Pt-based ones, the bandit also reveals model-derived hypothesis for how synthetic conditions affect the electrocatalysts’ performance near the identified local optima as autonomous inquiry proceeds, which is otherwise untenable from black-box ones. Incorporating chemistry-informed hypothesis into the decision-making bandit is generally applicable to any chemistry problem and offers a framework for autonomous investigation, advancing hypothesis generation for catalyst’s design principles beyond simple optimization.
Versions
Related
- Catalytic Metal–Organic Framework Membranes: Advances in Electrocatalysis, Photocatalysis, and Thermocatalysis
- Graph Symbolic Distillation: Decoding Graph Data into Interpretable Formulas across Materials and Chemistry
- Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations?
- DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
- An interpretable framework applying protein words to predict protein–small molecule complementary pairing rules
BibTeX
@article{lai2026chemistryinfused,
title = {{Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis}},
author = {Yi-An Lai and Muxin Xiong and Jingwen Sun and Aijian Huang and Max Van Fleet and Hongyuan Sheng and Jennifer Kim and Felisha Kuo and Tai Ying Lai and Xuian-Rou Lin and Yu-An Chen and Weitong Zhang and Hao Ming Chen and Chong Liu},
journal = {Nature Communications},
year = {2026},
month = oct,
doi = {10.1038/s41467-026-78335-w},
url = {https://www.nature.com/articles/s41467-026-78335-w},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Chemistry-infused bandit framework for interpretable autonomous campaign of electrocatalysis
AU - Yi-An Lai
AU - Muxin Xiong
AU - Jingwen Sun
AU - Aijian Huang
AU - Max Van Fleet
AU - Hongyuan Sheng
AU - Jennifer Kim
AU - Felisha Kuo
AU - Tai Ying Lai
AU - Xuian-Rou Lin
AU - Yu-An Chen
AU - Weitong Zhang
AU - Hao Ming Chen
AU - Chong Liu
PY - 2026
DA - 2026/10/23
JO - Nature Communications
DO - 10.1038/s41467-026-78335-w
UR - https://www.nature.com/articles/s41467-026-78335-w
AB - Autonomous experimentation offers a time-efficient route towards accelerated catalyst discovery, but current practices often rely on black-box models that are difficult to interpret. Here we demonstrate the paradigm of interpretable autonomous exploration of a 12-dimensional space in the electrocatalytic hydrogen evolution reaction by integrating an interpretable decision-making artificial intelligence with a fully automated electrochemical platform. Guided by a human’s chemistry-informed hypothesis, a chemistry-infused bandit is established to reflect the locally quadratic approximation between synthetic conditions and electrocatalytic activities near the explored optimum region. Not only does such a decision-making bandit lead to the discovery of previously unreported, earth-abundant electrocatalysts at least comparable to Pt-based ones, the bandit also reveals model-derived hypothesis for how synthetic conditions affect the electrocatalysts’ performance near the identified local optima as autonomous inquiry proceeds, which is otherwise untenable from black-box ones. Incorporating chemistry-informed hypothesis into the decision-making bandit is generally applicable to any chemistry problem and offers a framework for autonomous investigation, advancing hypothesis generation for catalyst’s design principles beyond simple optimization.
SN - 2041-1723
ER -