LoopRAG: A Closed-Loop Multi-Agent RAG Framework for Interactive Semantic Question Answering in Smart Buildings
Buildings · 01.01.2026 · 16 (1) · 196
DOI: 10.3390/buildings16010196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Buildings, online erschienen am 01.01.2026. Verfasst von Junqi Bai und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanghai Urban Digital Transformation Special Fund.
Abstract (Originalsprache)
With smart buildings being widely adopted in urban digital transformation, interactive semantic question answering (QA) systems serve as a crucial bridge between user intent and environmental response. However, they still face substantial challenges in semantic understanding and dynamic reasoning. Most existing systems rely on static frameworks built upon Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), which suffer from rigid prompt design, breakdowns in multi-step reasoning, and inaccurate generation. To tackle these issues, we propose LoopRAG, a multi-agent RAG architecture that incorporates a Plan–Do–Check–Act (PDCA) closed-loop optimization mechanism. The architecture formulates a dynamic QA pipeline across four stages: task parsing, knowledge extraction, quality evaluation, and policy feedback, and further introduces a semantics-driven prompt reconfiguration algorithm and a heterogeneous knowledge fusion module. These components strengthen multi-source information handling and adaptive reasoning. Experiments on HotpotQA, MultiHop-RAG, and an in-house building QA dataset demonstrate that LoopRAG significantly outperforms conventional RAG systems in key metrics, including context recall of 90%, response relevance of 72%, and answer accuracy of 88%. The results indicate strong robustness and cross-task generalization. This work offers both theoretical foundations and an engineering pathway for constructing trustworthy and scalable semantic QA interaction systems in smart building settings.
Förderung
- Shanghai Urban Digital Transformation Special Fund
Zitieren
APA
Bai, J., Ning, D., You, Y., & Chen, J. (2026). LoopRAG: A Closed-Loop Multi-Agent RAG Framework for Interactive Semantic Question Answering in Smart Buildings. Buildings, 16(1), 196. https://doi.org/10.3390/buildings16010196
Vancouver
Bai J, Ning D, You Y, Chen J. LoopRAG: A Closed-Loop Multi-Agent RAG Framework for Interactive Semantic Question Answering in Smart Buildings. Buildings. 2026;16(1):196. doi:10.3390/buildings16010196
BibTeX
@article{Bai2026,
author = {Bai, Junqi and Ning, Dejun and You, Yuxuan and Chen, Jiyan},
title = {LoopRAG: A Closed-Loop Multi-Agent RAG Framework for Interactive Semantic Question Answering in Smart Buildings},
journal = {Buildings},
year = {2026},
volume = {16},
number = {1},
pages = {196},
doi = {10.3390/buildings16010196}
}
EUVIMED