Journal article · 2026 · Open access

CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design

Xingyu Wang, Zihao Jiao, Ziyun Wang

SmartMat, 7(2) · Published 1 April 2026 · DOI 10.1002/smm2.70080

Open full textCite this paper

In brief

“CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design” is a 2026 journal article by Xingyu Wang and 2 co-authors, published in SmartMat. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at SmartMat.

Citations
0
References
50
Authors
3

Abstract

Despite advances in computational catalysis, the complexity of theoretical calculations and specialised expertise requirements limit the broader adoption of catalyst design tools. This work introduces CatPath‐GPT, a mixture‐of‐experts framework that democratizes computational catalyst design by integrating three AI specialists: product prediction (77.2% accuracy), computational planning, and automated code generation through a unified BERT‐based router. Experimental validation through two case studies demonstrates practical impact: systematic screening of Cu x Zn 1 − x catalysts identifies optimal compositions for selective CO 2 RR (Cu 75 Zn 25 for ethanol), while high‐throughput metal oxide screening reproduces Nørskov's classical scaling relationships and identifies high‐activity materials. Benchmarking against GPT‐4 and Mistral‐7B demonstrates superior performance across catalyst‐related tasks, particularly in modeling complex surface reactions. The open‐source framework enables researchers without computational expertise to perform advanced catalyst design, potentially transforming how catalytic materials are discovered and optimized.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, X., Jiao, Z., & Wang, Z. (2026). CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design. SmartMat, 7(2). https://doi.org/10.1002/smm2.70080

MLA 9

Wang, Xingyu, et al. “CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design.” SmartMat, vol. 7, no. 2, 2026. https://doi.org/10.1002/smm2.70080.

Chicago

Wang, Xingyu, Zihao Jiao, and Ziyun Wang. 2026. “CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design.” SmartMat 7 (2). https://doi.org/10.1002/smm2.70080.

Harvard

Wang, X., Jiao, Z. and Wang, Z. (2026) ‘CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design’, SmartMat, 7(2). doi:10.1002/smm2.70080.

IEEE

X. Wang, Z. Jiao, and Z. Wang, “CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design,” SmartMat, vol. 7, no. 2, 2026, doi: 10.1002/smm2.70080.

BibTeX

@article{wang2026catpath,
  title     = {{CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design}},
  author    = {Wang, Xingyu and Jiao, Zihao and Wang, Ziyun},
  journal   = {SmartMat},
  year      = {2026},
  volume    = {7},
  number    = {2},
  doi       = {10.1002/smm2.70080},
  url       = {https://doi.org/10.1002/smm2.70080}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • mixture of experts
  • product prediction
  • automatic code generation
  • Cu-Zn catalyst

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Wang, X., Jiao, Z., & Wang, Z. (2026). CatPath‐GPT: A Mixture of Experts System for Computational Catalyst Design. SmartMat, 7(2). https://doi.org/10.1002/smm2.70080

How many times has this paper been cited?

0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at SmartMat: sign in and open the full text from this page.

Who wrote this paper?

Xingyu Wang, Zihao Jiao, Ziyun Wang.

What is the DOI of this paper?

10.1002/smm2.70080, permanently at https://doi.org/10.1002/smm2.70080. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.