Metraipolis › archive › dc_83965ff12409
Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design — arXiv:2608.07978
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07978
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:00:55.314Z
- SHA-256 of the archived text
058dad7bfafdb049f5a4e9a163eb958c5d36da87f574865911002cf88b4a7132- Stable URL of this page
https://metraipolis.com/documento/dc_83965ff12409
How to cite
Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design — arXiv:2608.07978 — arXiv (en), https://arxiv.org/abs/2608.07978 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83965ff12409 (Metraipolis archive dc_83965ff12409, sha256 058dad7bfafdb049f5a4e9a163eb958c5d36da87f574865911002cf88b4a7132)
BibTeX
@misc{dc83965ff12409,
title = {Verication-driven closed-loop multi-agent large language modelframework for code-compliant structural design — arXiv:2608.07978},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07978},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83965ff12409; sha256 058dad7bfafdb049f5a4e9a163eb958c5d36da87f574865911002cf88b4a7132},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07978. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent large language model(LLM)systems are applied to structural design,yet most use one-shot generation and cannot verify their output,leaving themill-suited to safety-critical this http URL than trusting LLM self-correction,thisframework injects feedback from an external physics-based verier into a closedrepair this http URL framework couples a three-layernite-element verication systemwith a dual-node this http URL 1 turns code violations into hard repair constraints,Node 2 turns a four-dimensional quality score into safety-rst soft constraints,and a retrieval-augmented code base makes every violation traceable to a this http URL structure types and 44 cases,code compliance rises from 56.8%to 98.6%and the composite score from 63.8 to 71.4(p<0.000001),using about 5.8% this http URL either node degrades performance,and compliance does notchange detectably across the two backbone LLMs tested,indicating that it ishere attributed to the external verier rather than the this http URL framework,the 44-case benchmark and all experiment scripts are released as open source forreplicability. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.07978 — 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 2026-10-19T09:00:31.475Z 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).