@article{Liu2025, 
author = {Mingzhe Liu and Liang Zhang and Jianli Chen and Wei-An Chen and Zhiyao Yang and L. James Lo and Jin Wen and Zheng O’Neill},
title = {Large language models for building energy applications: Opportunities and challenges},
year = {2025},
journal = {Building Simulation},
volume = {18},
number = {2},
pages = {225-234},
keywords = {large language models, building energy applications, artificial intelligence, energy management optimization, LLM-as-agent workflows},
url = {https://www.sciopen.com/article/10.1007/s12273-025-1235-9},
doi = {10.1007/s12273-025-1235-9},
abstract = {Large language models (LLMs) are gaining attention due to their potential to enhance efficiency and sustainability in the building domain, a critical area for reducing global carbon emissions. Built on transformer architectures, LLMs excel at text generation and data analysis, enabling applications such as automated energy model generation, energy management optimization, and fault detection and diagnosis. These models can potentially streamline complex workflows, enhance decision-making, and improve energy efficiency. However, integrating LLMs into building energy systems poses challenges, including high computational demands, data preparation costs, and the need for domain-specific customization. This perspective paper explores the role of LLMs in the building energy system sector, highlighting their potential applications and limitations. We propose a development roadmap built on in-context learning, domain-specific fine-tuning, retrieval augmented generation, and multimodal integration to enhance LLMs’ customization and practical use in this field. This paper aims to spark ideas for bridging the gap between LLMs capabilities and practical building applications, offering insights into the future of LLM-driven methods in building energy applications.}
}