{
  "abstract": "Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and neuronal response. Predictive accuracy cannot settle the question: a real mechanistic change and an error in the computational twin leave the same signature in sparse observations. We formalize this twin confounding and reason over a joint mechanism--discrepancy belief, designing experiments that separate the two. NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism--Intervention--Observation--Outcome (MIOY) graph, whose supported relations compile into executable programs carrying discrepancy-adjusted acceptance bounds. We evaluate on simulated brain-fluid tracer-transport worlds adjudicated by an independently frozen finer-mesh reference solver, and on donor-disjoint public current-clamp recordings of cortical neurons. Counting only relations that reach a certified terminal status, and scoring abstentions as unresolved for every method, at a matched budget of 16 experiments over 32 source units NeuronDiscover resolves 4.0 relations per assigned world against 3.4 for the strongest baseline and 3.2 without graph revision, at 5% false support and 82% scope accuracy. Joint mechanism--discrepancy acquisition resolves 3.8 relations versus 2.9 for plug-in expected information gain; discrepancy-adjusted verification lowers accepted-program failure from 15% to 9% at 60% acceptance coverage; and transfer to the recordings yields 1.94 versus 1.53 relations per assigned world. Correctness is adjudicated within declared model worlds and archival recordings.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.35338",
  "author_total": 4,
  "authors": [
    {
      "name": "Haowei Xu"
    },
    {
      "name": "Wanyi Fu"
    },
    {
      "name": "Hongbin Han"
    },
    {
      "name": "Zhaoheng Xie"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/25nz980rb4htd.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.35338",
  "fulltext_url": null,
  "id": "25nz980rb4htd",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.35338",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "q-bio.NC"
    ],
    [
      "openalex",
      "1207|Philosophy and History of Science"
    ]
  ],
  "openalex": "W7214700129",
  "pdf_url": "https://arxiv.org/pdf/2609.35338",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/25nz980rb4htd.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:29:36Z",
      "native_id": "2609.35338",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.35338"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.NC",
      "subfield": "neuroscience"
    }
  ],
  "title": "NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models",
  "title_text": "NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models",
  "type": "preprint",
  "updated_at": "2026-10-30T12:29:36Z",
  "url": "https://research.draconitic.com/paper/25nz980rb4htd",
  "venue": "arXiv",
  "versions": []
}