Metraipolis › archive › dc_cbcf7a73a8d6
Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering — arXiv:2608.08038
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08038
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:00:55.365Z
- SHA-256 of the archived text
2b246928681839557d92d12b2f64af60151d185ac41cfb80c4caed45f9a5b996- Stable URL of this page
https://metraipolis.com/documento/dc_cbcf7a73a8d6
How to cite
Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering — arXiv:2608.08038 — arXiv (en), https://arxiv.org/abs/2608.08038 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbcf7a73a8d6 (Metraipolis archive dc_cbcf7a73a8d6, sha256 2b246928681839557d92d12b2f64af60151d185ac41cfb80c4caed45f9a5b996)
BibTeX
@misc{dccbcf7a73a8d6,
title = {Stateful Multi-Agent LLMs for Cross-View Interface Alignment in Automotive Model-Based Systems Engineering — arXiv:2608.08038},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08038},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbcf7a73a8d6; sha256 2b246928681839557d92d12b2f64af60151d185ac41cfb80c4caed45f9a5b996},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08038. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While Large Language Models (LLMs) can accelerate Model-Based Systems Engineering (MBSE) for software-defined vehicles, their probabilistic nature causes "architectural drift", fabricating interfaces in behavioral views that lack structural foundations. To enforce deterministic interface alignment, we propose a stateful, multi-agent validation pipeline. The framework utilizes a sequential generation matrix (Class->Activity->Sequence) and Vehicle Signal Specification (VSS)-grounded Retrieval-Augmented Generation (RAG). An independent AI Validator Agent dynamically audits outputs against a strict error taxonomy, triggering state-preserving backtracking loops to resolve incompatibilities. Evaluated on an Advanced Driver Assistance System (ADAS) scenario, standard RAG yielded 0% Entity Traceability. Conversely, our multi-agent workflow eradicated cross-phase hallucinations, achieving 97% Entity Traceability, 87% Signal Conservation, and an 85% F1-score. This proves adversarial auditing enables LLMs to reliably synthesize zero-error MBSE architectures. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.08038 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:00:31.476Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).