Journal article · 2026 · Open access
Guiding generative models to uncover diverse and novel crystals via reinforcement learning
Nature Machine Intelligence, 8(7), 1087–1099 · Published 6 July 2026 · DOI 10.1038/s42256-026-01262-4
In brief
“Guiding generative models to uncover diverse and novel crystals via reinforcement learning” is a 2026 journal article by Hyunsoo Park and Aron Walsh, published in Nature Machine Intelligence. OpenAlex counts 31 citations as of 16 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Nature Machine Intelligence.
- Citations
- 31
- Most cited in
- 2026 (31)
- Field-weighted impact
- 32.17
- References
- 61
- Authors
- 2
Abstract
Discovering functional crystalline materials entails navigating an immense combinatorial design space. Although recent advances in generative artificial intelligence have enabled the sampling of chemically plausible compositions and structures, a fundamental challenge remains: the objective misalignment between the likelihood-based sampling in generative modelling and the targeted focus on underexplored regions where novel compounds reside. Here we introduce a reinforcement learning framework that guides latent denoising diffusion models in finding diverse and novel, yet thermodynamically viable, crystalline compounds. Our approach integrates group-relative policy optimization with verifiable, multi-objective rewards that jointly balance creativity, stability and diversity. Beyond de novo generation, we demonstrate enhanced property-guided design that preserves chemical validity while targeting desired functional properties. This approach establishes a modular foundation for controllable AI-driven inverse design that addresses the novelty–validity trade-off across the scientific discovery applications of generative models.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Park, H., & Walsh, A. (2026). Guiding generative models to uncover diverse and novel crystals via reinforcement learning. Nature Machine Intelligence, 8(7), 1087–1099. https://doi.org/10.1038/s42256-026-01262-4
MLA 9
Park, Hyunsoo, and Aron Walsh. “Guiding generative models to uncover diverse and novel crystals via reinforcement learning.” Nature Machine Intelligence, vol. 8, no. 7, 2026, pp. 1087–1099. https://doi.org/10.1038/s42256-026-01262-4.
Chicago
Park, Hyunsoo and Aron Walsh. 2026. “Guiding generative models to uncover diverse and novel crystals via reinforcement learning.” Nature Machine Intelligence 8 (7): 1087–1099. https://doi.org/10.1038/s42256-026-01262-4.
Harvard
Park, H. and Walsh, A. (2026) ‘Guiding generative models to uncover diverse and novel crystals via reinforcement learning’, Nature Machine Intelligence, 8(7), pp. 1087–1099. doi:10.1038/s42256-026-01262-4.
IEEE
H. Park and A. Walsh, “Guiding generative models to uncover diverse and novel crystals via reinforcement learning,” Nature Machine Intelligence, vol. 8, no. 7, pp. 1087–1099, 2026, doi: 10.1038/s42256-026-01262-4.
BibTeX
@article{park2026guiding,
title = {{Guiding generative models to uncover diverse and novel crystals via reinforcement learning}},
author = {Park, Hyunsoo and Walsh, Aron},
journal = {Nature Machine Intelligence},
year = {2026},
volume = {8},
number = {7},
pages = {1087--1099},
doi = {10.1038/s42256-026-01262-4},
url = {https://doi.org/10.1038/s42256-026-01262-4}
}
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
- reinforcement learning
- denoising diffusion probabilistic models
- generative models
- Group Relative Policy Optimization
- inverse design
- chemical validity
- thermodynamic feasibility
Work with this paper
Most-cited papers in Materials Science
- Electric Field Effect in Atomically Thin Carbon FilmsKostya S. Novoselov, Andre K. Geim, Sergey V. Morozov and 5 more · Science · 2004 · 67,474 citations
- Revised effective ionic radii and systematic studies of interatomic distances in halides and chalcogenidesROBERT D. SHANNON · Acta Crystallographica Section A · 1976 · 66,944 citations
- Ab initio molecular dynamics for liquid metalsGeorg Kresse, J. Häfner · Physical review. B, Condensed matter · 1993 · 46,320 citations
- Helical microtubules of graphitic carbonSumio Iijima · Nature · 1991 · 43,639 citations
- The rise of grapheneAndre K. Geim, Kostya S. Novoselov · Nature Materials · 2007 · 40,328 citations
Questions about this paper
How do I cite this paper in APA style?
Park, H., & Walsh, A. (2026). Guiding generative models to uncover diverse and novel crystals via reinforcement learning. Nature Machine Intelligence, 8(7), 1087–1099. https://doi.org/10.1038/s42256-026-01262-4
How many times has this paper been cited?
31 times, according to OpenAlex on 16 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 Nature Machine Intelligence: sign in and open the PDF from this page.
Who wrote this paper?
Hyunsoo Park, Aron Walsh.
What is the DOI of this paper?
10.1038/s42256-026-01262-4, permanently at https://doi.org/10.1038/s42256-026-01262-4. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 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.