Preprint · 2026 · Open access

Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI

Ruili Li, Rui Qi, Qingqing Mao, Ritankar Das, Beien Zhu, Yi Gao

arXiv (Cornell University) · Published 30 September 2026 · DOI 10.48550/arxiv.2609.39060

Open PDFView at the publisherCite this paper

In brief

“Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI” is a 2026 preprint by Ruili Li and 5 co-authors, published in arXiv (Cornell University). 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 arXiv (Cornell University).

Citations
0
References
38
Authors
6

Abstract

Artificial intelligence (AI) has expanded the accessible space for catalyst discovery, yet executing complex screening campaigns still requires constant human intervention to bridge high-level reaction objectives with underlying computational pipelines. Here, we present Autocata, a knowledge-embedded autonomous agent that scales catalytic expertise by encoding multistep reaction pathways into reusable, language-invocable capabilities. Powered by a Transformer pretrained on two million catalyst-adsorbate structures, the system incorporates a capability registry of 79 adsorbate-specialized generative models spanning complex reaction networks across carbon, nitrogen, oxygen, and hydrogen intermediates. Given a high-level natural-language prompt, Autocata deconstructs reaction networks, queries and configures matching generative models, generates candidate surface configurations, enforces physical and geometric validity filtering, and coordinates machine-learning potentials evaluations to rank promising materials. Crucially, the agent adaptively reconfigures workflows when encountering capability boundaries or task bottlenecks. We demonstrate these capabilities across CH4 activation, nitrogen reduction reaction (N2RR), and CO2-to-methanol pathways. By shifting from static toolkits to an adaptive, language-driven computational infrastructure, Autocata lowers the barrier for expert-level catalyst discovery and offers a scalable paradigm for self-driving catalytic research.

Cite this paper

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

APA 7

Li, R., Qi, R., Mao, Q., Das, R., Zhu, B., & Gao, Y. (2026). Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.39060

MLA 9

Li, Ruili, et al. “Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2609.39060.

Chicago

Li, Ruili, Rui Qi, Qingqing Mao, Ritankar Das, Beien Zhu, and Yi Gao. 2026. “Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.39060.

Harvard

Li, R. et al. (2026) ‘Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI’, arXiv (Cornell University). doi:10.48550/arxiv.2609.39060.

IEEE

R. Li, R. Qi, Q. Mao, R. Das, B. Zhu, and Y. Gao, “Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2609.39060.

BibTeX

@misc{li2026autocata,
  title     = {{Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI}},
  author    = {Li, Ruili and Qi, Rui and Mao, Qingqing and Das, Ritankar and Zhu, Beien and Gao, Yi},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2609.39060},
  url       = {https://doi.org/10.48550/arxiv.2609.39060}
}

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

  • natural language prompts
  • machine learning interatomic potentials
  • CH4 activation
  • nitrogen reduction reaction
  • CO2-to-methanol conversion

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?

Li, R., Qi, R., Mao, Q., Das, R., Zhu, B., & Gao, Y. (2026). Autocata: Reaction-network-guided autonomous catalyst screening via capability-centric AI. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2609.39060

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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Ruili Li, Rui Qi, Qingqing Mao, Ritankar Das, Beien Zhu, Yi Gao.

What is the DOI of this paper?

10.48550/arxiv.2609.39060, permanently at https://doi.org/10.48550/arxiv.2609.39060. 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.