{
  "abstract": "Translating virtually designed drug molecules into executable synthesis protocols is essential for connecting computational discovery with automated synthesis. However, most retrosynthesis methods focus on precursor generation, offer limited route diversity, and lack the detailed reaction conditions required for executable protocols. Here, we present Syn-RRAG, a retrieval-augmented LLM-driven synthesis agent connecting virtual screening with automated synthesis and validation. Syn-RRAG integrates initial retrosynthetic prediction, reaction-precedent retrieval and hierarchical refinement to generate structured protocols with complete experimental parameters. Its local generative model searches over complete reaction hypotheses rather than relying solely on token-level beam search, enabling exploration of feasible routes with distinct reaction classes and bond disconnections. It achieved strong retrosynthesis performance on two patent-derived reaction datasets. Syn-RRAG further generated executable plans for three virtually screened drug candidates, all of which were synthesized and validated on an automated platform. These results establish a workflow connecting virtual molecular design, synthesis planning and experimental validation.",
  "abstract_shown": true,
  "affiliations": [
    "Shanghai Academy of Artificial Intelligence for Science",
    "Golab Inc.",
    "Artificial Intelligence Innovation and Incubation Institute, Fudan University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shan Zhu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Xin Chen"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Pinqi Wang"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Quan Jiang"
    },
    {
      "affs": [
        2
      ],
      "name": "Mengzhu Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Qimeng Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Guoyun Zhao"
    },
    {
      "affs": [
        0,
        2
      ],
      "name": "Yuan Qi"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Fenglei Cao"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Li-Cheng Xu",
      "orcid": "0000-0002-9553-0412"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9aby3qpdv7xfj.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15008409/v1",
  "fulltext_url": null,
  "id": "9aby3qpdv7xfj",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008409/v1",
  "language": null,
  "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",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7211900291",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008409/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-07",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/9aby3qpdv7xfj.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15008409",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15008409/v1"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "A retrieval-augmented agent bridges virtual screening and automated synthesis",
  "title_text": "A retrieval-augmented agent bridges virtual screening and automated synthesis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/9aby3qpdv7xfj",
  "venue": "ChemRxiv",
  "versions": []
}