{
  "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.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Materials, Imperial College London, London, UK"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hyunsoo Park",
      "orcid": "0000-0001-9388-173X"
    },
    {
      "affs": [
        0
      ],
      "name": "Aron Walsh",
      "orcid": "0000-0001-5460-7033"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/edc0hzjxrchwx.bib",
  "cited_by": 29,
  "doi": "10.1038/s42256-026-01262-4",
  "fulltext_url": null,
  "id": "edc0hzjxrchwx",
  "issns": [
    "2522-5839"
  ],
  "landing_url": "https://doi.org/10.1038/s42256-026-01262-4",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W4416158865",
  "pdf_url": "https://www.nature.com/articles/s42256-026-01262-4.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-06",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/edc0hzjxrchwx.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T13:21:19Z",
      "native_id": "W4416158865",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s42256-026-01262-4"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Guiding generative models to uncover diverse and novel crystals via reinforcement learning",
  "title_text": "Guiding generative models to uncover diverse and novel crystals via reinforcement learning",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:22Z",
  "url": "https://research.draconitic.com/paper/edc0hzjxrchwx",
  "venue": "Nature Machine Intelligence",
  "versions": []
}