{
  "abstract": "Making a new reaction often requires chemical knowledge that does not yet exist. Self-driving laboratories and language-model agents now plan, run and optimize experiments rapidly1–3, but deciding what to ask next still requires a chemist in the loop4. Here we report AIChemist, a robotic chemist for what we call constructive chemical discovery. It decides what to ask next from its own results, settles each question by calculation or experiment, and builds the next design on the answer. Given a silyl-radical-relay concept, AIChemist developed an asymmetric three-component silylcyanation: it established that the solvent effect depended on the oxidant formulation and built the next formulation on this finding, raising the yield from 20% to 67% at 88% enantiomeric excess. For an intermediate of the insecticide broflanilide, it designed a photoredox/nickel C–N coupling route free of nitro-group transformations, at lower estimated cost than the conventional route. When the base favoured by calculation performed poorly, it withdrew that premise and rebuilt the search around the reaction medium, where non-polar toluene raised the product's HPLC yield from 43% to 86%. In both cases, each conclusion extended what the system knew and became the starting point for the next. These results demonstrate a framework for autonomous chemical discovery in which chemical understanding and experimental design evolve together within a closed loop.",
  "abstract_shown": true,
  "affiliations": [
    "Shanghai Innovation Institute",
    "Department of Computer Science and Engineering",
    "Chinese University of Hong Kong",
    "School of Mathematics, Computing, and Data Science",
    "New York University",
    "Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development",
    "SII–ECNU Joint Autonomous Chemistry Laboratory, School of Chemistry and Molecular Engineering, East China Normal University",
    "AINORO Inc.",
    "Department of Chemistry",
    "University of Chicago",
    "Department of Chemistry and Chemical Biology",
    "Harvard University",
    "Division of Biology and Biological Engineering",
    "California Institute of Technology",
    "Department of Chemical and Biological Engineering",
    "Northwestern University",
    "Department of Pathology",
    "Stanford University",
    "Acceleration Consortium",
    "University of Toronto"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 24,
  "authors": [
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Yuzhi Richie Xu",
      "orcid": "0000-0002-3325-5427"
    },
    {
      "affs": [
        3,
        4
      ],
      "name": "Max Wang"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Zilong Yan"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Yu Jiang"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Yong Lu"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Yuting Wang"
    },
    {
      "affs": [
        0
      ],
      "name": "Haohui Que"
    },
    {
      "affs": [
        0
      ],
      "name": "Zhengming Zhang"
    },
    {
      "affs": [
        0
      ],
      "name": "Letian Chen"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Zhenjia Gan"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Haotian Wu"
    },
    {
      "affs": [
        7
      ],
      "name": "Yilin Wei"
    },
    {
      "affs": [
        7
      ],
      "name": "Chengyi Xing"
    },
    {
      "affs": [
        0
      ],
      "name": "Wenxi Zhai"
    },
    {
      "affs": [
        0
      ],
      "name": "Bowen Li"
    },
    {
      "affs": [
        8,
        9
      ],
      "name": "Daqian Bian"
    },
    {
      "affs": [
        10,
        11
      ],
      "name": "Yuli Li"
    },
    {
      "affs": [
        12,
        13
      ],
      "name": "Chengwei Ju"
    },
    {
      "affs": [
        14,
        15
      ],
      "name": "Jiankai Ge"
    },
    {
      "affs": [
        16,
        17
      ],
      "name": "Yingcheng Wu"
    },
    {
      "affs": [
        18,
        19
      ],
      "name": "Yuanqing Wang"
    },
    {
      "affs": [
        1,
        2
      ],
      "name": "Pheng Ann Heng"
    },
    {
      "affs": [
        5,
        6
      ],
      "name": "Dong Xing"
    },
    {
      "affs": [
        0,
        5,
        6
      ],
      "name": "Tong Zhu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2dgt2348v8vyq.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15011027/v1",
  "fulltext_url": null,
  "id": "2dgt2348v8vyq",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011027/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",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7223677679",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011027/v1",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-25",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/2dgt2348v8vyq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:26Z",
      "native_id": "10.26434/chemrxiv.15011027",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15011027/v2"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Constructive chemical discovery through autonomous reasoning and experiment",
  "title_text": "Constructive chemical discovery through autonomous reasoning and experiment",
  "type": "preprint",
  "updated_at": "2026-10-31T00:20:31Z",
  "url": "https://research.draconitic.com/paper/2dgt2348v8vyq",
  "venue": "ChemRxiv",
  "versions": []
}