{
  "abstract": "Large language models offer flexible semantic reasoning for intelligent-vehicle interfaces, but probabilistic outputs, multi-agent disagreement, and provider failures complicate safety-sensitive use. We developed SCI-Proposed-v1.0, a lightweight multi-agent semantic decision architecture that combines transparent risk-informed routing with an independent Safety Validator and deterministic local Runtime Fallback. The system produces canonical semantic actions rather than trajectories or direct vehicle-control commands. In a frozen confirmatory benchmark of 150 unseen Base Scenarios, each represented by three reviewed language variants, SCI-Proposed completed 360/450 inputs (80.0%), compared with 169/450 (37.6%) for EI-MAS and 155/450 (34.4%) for a Single LLM. Language variants were treated as repeated observations within each Base Scenario, and all methods used the same frozen model configuration. Base-scenario paired differences were 0.4244 (95% confidence interval, 0.3489–0.5000; p < 0.001) and 0.4556 (95% confidence interval, 0.3800–0.5311; p < 0.001), respectively. Complete Safety Requirement Satisfaction was 316/360 (87.8%) versus 101/360 (28.1%) for EI-MAS. In frozen ablation, removing the Safety Validator reduced its prespecified endpoint by 0.2767 (p < 0.001), and removing Runtime Fallback reduced represented-failure recovery by 0.3667 (p = 0.00195). Exact three-of-three canonical action-set stability was 27/30 (90.0%). In prespecified isolated-sandbox hardware-in-the-loop validation, Scientific Task Success was 25/30, Safety Enforcement Success was 7/7 applicable cases, and Runtime Recovery was 4/6 applicable cases. Across these complementary, prespecified stages, separating generative reasoning from independent safety validation and class-bounded local runtime recovery materially improved semantic-decision dependability under the tested qwen-plus/DashScope configuration, frozen semantic policy, and represented fault classes. These findings do not establish broader vehicle-system safety, physical-control reliability, arbitrary-fault recovery, or deployment readiness.",
  "abstract_shown": true,
  "affiliations": [
    "Beijing Information Technology College, Beijing, China."
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Wei Dang",
      "orcid": "0009-0000-0643-2689"
    },
    {
      "affs": [
        0
      ],
      "name": "Lijun Gao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5xtv7tt2xa3fz.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0357928",
  "fulltext_url": "https://europepmc.org/articles/PMC13722150",
  "id": "5xtv7tt2xa3fz",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0357928",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Biology and Life Sciences"
    ],
    [
      "heading",
      "Classical Mechanics"
    ],
    [
      "heading",
      "Cognitive Psychology"
    ],
    [
      "heading",
      "Cognitive Science"
    ],
    [
      "heading",
      "Commerce"
    ],
    [
      "heading",
      "Comparators"
    ],
    [
      "heading",
      "Damage Mechanics"
    ],
    [
      "heading",
      "Economics"
    ],
    [
      "heading",
      "Electrical Engineering"
    ],
    [
      "heading",
      "Electrical Faults"
    ],
    [
      "heading",
      "Electronics"
    ],
    [
      "heading",
      "Electronics Engineering"
    ],
    [
      "heading",
      "Engineering and Technology"
    ],
    [
      "heading",
      "Epidemiology"
    ],
    [
      "heading",
      "Equipment"
    ],
    [
      "heading",
      "Language"
    ],
    [
      "heading",
      "Material Fatigue"
    ],
    [
      "heading",
      "Materials Physics"
    ],
    [
      "heading",
      "Materials Science"
    ],
    [
      "heading",
      "Medical Risk Factors"
    ],
    [
      "heading",
      "Medicine and Health Sciences"
    ],
    [
      "heading",
      "Neuroscience"
    ],
    [
      "heading",
      "Physical Sciences"
    ],
    [
      "heading",
      "Physics"
    ],
    [
      "heading",
      "Protective Clothing"
    ],
    [
      "heading",
      "Protective Footwear"
    ],
    [
      "heading",
      "Psychology"
    ],
    [
      "heading",
      "Public and Occupational Health"
    ],
    [
      "heading",
      "Reflection"
    ],
    [
      "heading",
      "Research Article"
    ],
    [
      "heading",
      "Safety"
    ],
    [
      "heading",
      "Safety Equipment"
    ],
    [
      "heading",
      "Social Sciences"
    ],
    [
      "heading",
      "Vendors"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Language"
    ],
    [
      "plos",
      "/Engineering and technology/Electrical engineering/Electrical faults"
    ],
    [
      "plos",
      "/Engineering and technology/Electronics engineering/Electronics/Comparators"
    ],
    [
      "plos",
      "/Engineering and technology/Equipment/Safety equipment/Protective clothing/Protective footwear"
    ],
    [
      "plos",
      "/Medicine and health sciences/Epidemiology/Medical risk factors"
    ],
    [
      "plos",
      "/Medicine and health sciences/Public and occupational health/Safety/Safety equipment/Protective clothing/Protective footwear"
    ],
    [
      "plos",
      "/Physical sciences/Materials science/Materials physics/Material fatigue"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Classical mechanics/Damage mechanics/Material fatigue"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Classical mechanics/Reflection"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Materials physics/Material fatigue"
    ],
    [
      "plos",
      "/Social sciences/Economics/Commerce/Vendors"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Language"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://europepmc.org/articles/PMC13722150?pdf=render",
  "pmcid": "PMC13722150",
  "pmid": "42961879",
  "published": "2026-10-30",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/5xtv7tt2xa3fz.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:20:55Z",
      "native_id": "10.1371/journal.pone.0357928",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0357928"
    },
    {
      "first_seen": "2026-11-02T03:21:21Z",
      "native_id": "MED:42961879",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42961879"
    },
    {
      "first_seen": "2026-11-03T12:22:42Z",
      "native_id": "PMC13722150",
      "source": "pmc",
      "url": "https://doi.org/10.1371/journal.pone.0357928"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "chemistry",
      "origin": "plos:materials science",
      "subfield": "materials-polymers"
    },
    {
      "field": "medicine",
      "origin": "plos:epidemiology",
      "subfield": "epidemiology-public-health"
    },
    {
      "field": "physics",
      "origin": "heading:Physics",
      "subfield": "general"
    }
  ],
  "title": "Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems",
  "title_text": "Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems",
  "type": "peer-reviewed",
  "updated_at": "2026-11-03T12:22:42Z",
  "url": "https://research.draconitic.com/paper/5xtv7tt2xa3fz",
  "venue": "PLOS One",
  "versions": []
}