Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems
PLOS One · 30.10.2026 · 21 (10) · e0357928
DOI: 10.1371/journal.pone.0357928 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 30.10.2026. Verfasst von Wei Dang und 1 weiteren Autor:innen. Beteiligte Einrichtung: Beijing Information Technology College, Beijing, China. Hauptthemen laut MEDLINE: Safety, Decision Making. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Beijing Information Technology College, Beijing, China.
ORCID-Profile: Wei Dang
Zitieren
APA
Dang, W., & Gao, L. (2026). Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems. PLOS One, 21(10), e0357928. https://doi.org/10.1371/journal.pone.0357928
Vancouver
Dang W, Gao L. Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems. PLOS One. 2026;21(10):e0357928. doi:10.1371/journal.pone.0357928
BibTeX
@article{Dang2026,
author = {Dang, Wei and Gao, Lijun},
title = {Safety-constrained and runtime-assured LLM multi-agent decision making for intelligent vehicle systems},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {10},
pages = {e0357928},
doi = {10.1371/journal.pone.0357928}
}
EUVIMED