{
  "abstract": "Biomolecular generators are often adapted with reward feedback to improve task-specific utility, but pushing utility alone can concentrate generation on a narrow family of candidates. Maintaining diversity is difficult because sample diversity is a set-level property. We introduce Supergroup Relative Policy Optimization (SGRPO), a flexible GRPO-style framework that directly constructs rewards from set-level diversity. For each condition, SGRPO samples a supergroup of candidate sets, compares their diversity under the same condition, and redistributes the group diversity reward to individual rollouts through leave-one-out diversity contributions before combining it with rollout-level utility. This design decouples SGRPO from a particular generator, utility reward, or diversity metric, and allows instantiation with different GRPO-style approaches. We evaluate SGRPO on three main settings: de novo small-molecule design, pocket-based small-molecule design, and de novo protein design, instantiating it with both GRPO and Coupled-GRPO across autoregressive and discrete diffusion generators. Across decoding sweeps, SGRPO expands the utility-diversity Pareto frontier and achieves the best frontier-level metrics relative to baselines. Our analyses further show that direct set-level diversity rewards remain effective with small groups and help preserve broader generation-distribution coverage during post-training. The code is available at https://github.com/IDEA-XL/SGRPO.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2605.08659",
  "author_total": 8,
  "authors": [
    {
      "name": "Xinwu Ye"
    },
    {
      "name": "He Cao"
    },
    {
      "name": "Hao Li"
    },
    {
      "name": "Bin Feng"
    },
    {
      "name": "Zijing Liu"
    },
    {
      "name": "Xiangru Tang"
    },
    {
      "name": "Yu Li"
    },
    {
      "name": "Shenghua Gao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/apzbe0gme2pa4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.08659",
  "fulltext_url": null,
  "id": "apzbe0gme2pa4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.08659",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CE"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7160945995",
  "pdf_url": "https://arxiv.org/pdf/2605.08659",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/apzbe0gme2pa4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:23Z",
      "native_id": "2605.08659",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.08659"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    }
  ],
  "title": "Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization",
  "title_text": "Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:23Z",
  "url": "https://research.draconitic.com/paper/apzbe0gme2pa4",
  "venue": "arXiv",
  "versions": []
}