{
  "abstract": "AI models, including large language models, are increasingly integrated into scientific discovery workflows, yet they remain prone to hallucination. In experimental sciences, such errors translate directly into failed wet-lab validations and wasted resources; in self-improving agentic systems, confident errors risk being reinforced rather than corrected. Retrosynthesis provides a representative example of this failure mode: existing models can generate chemically plausible routes, but cannot reliably determine which routes are experimentally feasible. We define \\textbf{Chemical Hallucination} as a route that appears valid yet fails under competing reactive sites, unresolved selectivity, or missing mechanistic support, a failure largely invisible to the Recall@$K$ metric. We introduce \\textbf{SureRoute}, a chemical verifier-anchored retrosynthesis platform that suppresses Chemical Hallucination. SureRoute combines a multi-model ensemble, data asset retrieval, and \\textbf{ChemHarness}, an executable chemical intuition engine for route verification and reliability-first ranking. On a benchmark of 350 real-world industrial targets, SureRoute reaches 74.3\\% recall@1, 2.2--3.5$\\times$ that of seven single-step models and three frontier LLMs, while cutting top-1 Chemical Hallucination to 4.6\\%, a 4--6$\\times$ reduction relative to frontier LLMs. As a model-agnostic reranker, ChemHarness drives detectable hallucination toward near-zero across arbitrary backbone candidates. SureRoute shows that reliable scientific AI requires not only strong generation, but executable verification.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.05450",
  "author_total": 4,
  "authors": [
    {
      "name": "Jieli Zhou"
    },
    {
      "name": "Naiwu Chen"
    },
    {
      "name": "Longzhang Liu"
    },
    {
      "name": "Peiyu Zhang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/damdzzcweydh2.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.05450",
  "fulltext_url": null,
  "id": "damdzzcweydh2",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.05450",
  "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.MA"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7212016129",
  "pdf_url": "https://arxiv.org/pdf/2609.05450",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/damdzzcweydh2.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:02Z",
      "native_id": "2609.05450",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.05450"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "SureRoute: Toward a Hallucination-Free Self-Improving Platform for Retrosynthesis",
  "title_text": "SureRoute: Toward a Hallucination-Free Self-Improving Platform for Retrosynthesis",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:02Z",
  "url": "https://research.draconitic.com/paper/damdzzcweydh2",
  "venue": "arXiv",
  "versions": []
}