{
  "abstract": "Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organized large-scale exploration. Paper2Skill extracts transferable scientific decision knowledge from public sources and, together with expert-developed skills, supports research decisions. Self-Scaling Discovery expands exploration through parallel agents inheriting research context and decision-making capabilities across targets, scientific hypotheses, and discovery strategies. We introduce PharmAgents-Bench v0.1, comprising 121 questions across nine decision scenarios and three end-to-end tasks assessed with expert-defined process rubrics. PharmAgents2 outperforms evaluated baselines in most decision categories and achieves the highest process scores on all three end-to-end tasks. In three real-world studies, autonomous investigations generated findings subsequently supported by human-executed experiments. For LpxH, PharmAgents2 hypothesized a previously unreported allosteric site and screened compounds against it, identifying a novel inhibitor scaffold with experimentally confirmed inhibitory activity and binding. For JAK1, it prioritized a covalent inhibition strategy and nominated compounds with experimentally demonstrated activity. Starting from a known bioactive molecule, Self-Scaling Discovery explored candidate targets across the proteome and identified a new binding target, with the interaction subsequently confirmed experimentally. PharmAgents2 represents a prototype of a virtual pharmaceutical company, marking a step toward autonomous end-to-end drug discovery.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.07653",
  "author_total": 25,
  "authors": [
    {
      "name": "Haichuan Tan"
    },
    {
      "name": "Bowen Gao"
    },
    {
      "name": "Tao Huang"
    },
    {
      "name": "Jiaxin Tan"
    },
    {
      "name": "Xin Hong"
    },
    {
      "name": "Baoguo Yao"
    },
    {
      "name": "Yifei Wang"
    },
    {
      "name": "Zhichao Deng"
    },
    {
      "name": "Hanji Du"
    },
    {
      "name": "Dapeng Jiang"
    },
    {
      "name": "Yiheng Li"
    },
    {
      "name": "Weiwei Ma"
    },
    {
      "name": "Xin Ma"
    },
    {
      "name": "Yuqi Shi"
    },
    {
      "name": "Zixiang Wang"
    },
    {
      "name": "Kelin Wu"
    },
    {
      "name": "Tianxiang Wu"
    },
    {
      "name": "Wenxuan Xie"
    },
    {
      "name": "Jie Zang"
    },
    {
      "name": "Huiyu Zhang"
    },
    {
      "name": "Mojia Zhang"
    },
    {
      "name": "Yuying Zhang"
    },
    {
      "name": "Ya-Qin Zhang"
    },
    {
      "name": "Wei-Ying Ma"
    },
    {
      "name": "Yanyan Lan"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dw4f80emz235f.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.07653",
  "fulltext_url": null,
  "id": "dw4f80emz235f",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.07653",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.07653",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dw4f80emz235f.ris",
  "sources": [
    {
      "first_seen": "2026-11-06T18:21:35Z",
      "native_id": "2611.07653",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.07653"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "PharmAgents2: Towards Autonomous End-to-End Drug Discovery",
  "title_text": "PharmAgents2: Towards Autonomous End-to-End Drug Discovery",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:50Z",
  "url": "https://research.draconitic.com/paper/dw4f80emz235f",
  "venue": "arXiv",
  "versions": []
}