EUVIMEDEUVIMED entdecken
Crossref

MASHI: Multi-Agent Vision-Language System for Home Inspection

Zeyang Zheng, Seyed Hamidreza Nabaei, Amir Farzin Nikkhah, Hunter Frederick Lutz, Brad Campbell, Arsalan Heydarian

ACM Transactions on Sensor Networks · 07.11.2026

DOI: 10.1145/3859927 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Sensor Networks, online erschienen am 07.11.2026. Verfasst von Zeyang Zheng und 5 weiteren Autor:innen. Die Arbeit nennt 82 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Home inspection evaluates the visible components of a residential building and reports their deficiencies, safety concerns, and recommended actions. Vision–language models (VLMs) can describe what a photograph shows, but inspection findings also require regulatory knowledge, system-level assessment, and familiarity with inspection practice. We present MASHI, a multi-agent vision–language system that answers home inspection questions across the ten systems of the ASHI Standard of Practice. A planner agent routes each question to an ASHI system and assigns tasks to a perception agent and a system agent. The perception agent reports visual evidence from the question’s photograph. The system agent applies the agent skill of the selected ASHI system to the question, its task, and this evidence. When needed, it retrieves text and images through multimodal retrieval-augmented generation (RAG) from a knowledge base of 45 building code editions and 18 inspection reports. For evaluation, a semi-automated pipeline with human verification turns 84 other inspection reports into 32,554 question–answer pairs. Prometheus-2 and Phi-4 rate the answers on a five-level rubric. MASHI reaches a mean judge score of 4.083, higher than those of all other compared systems, including its single-agent variant. Every difference is statistically significant.

Zitieren

APA

Zheng, Z., Nabaei, S. H., Nikkhah, A. F., Lutz, H. F., Campbell, B., & Heydarian, A. (2026). MASHI: Multi-Agent Vision-Language System for Home Inspection. ACM Transactions on Sensor Networks. https://doi.org/10.1145/3859927

Vancouver

Zheng Z, Nabaei SH, Nikkhah AF, Lutz HF, Campbell B, Heydarian A. MASHI: Multi-Agent Vision-Language System for Home Inspection. ACM Transactions on Sensor Networks. 2026. doi:10.1145/3859927

BibTeX
@article{Zheng2026,
  author = {Zheng, Zeyang and Nabaei, Seyed Hamidreza and Nikkhah, Amir Farzin and Lutz, Hunter Frederick and Campbell, Brad and Heydarian, Arsalan},
  title = {MASHI: Multi-Agent Vision-Language System for Home Inspection},
  journal = {ACM Transactions on Sensor Networks},
  year = {2026},
  doi = {10.1145/3859927}
}
Kostenlos starten →