发表机构
School of Electrical Engineering
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对智能家居LLM智能体韧性不足问题，结合监督学习与优化提示，在HomeAssistant上评估多种LLM及ReAct、Reflexion范式，发现微调更有效，但后者在故障响应上有潜力。
AI 中文摘要
智能家居和智能设备在全球数百万家庭中正变得越来越普及。随着人工智能的兴起，智能家居行业正迅速加强其集成，以管理常见的智能家居任务。然而，现有关于大型语言模型（LLM）作为智能家居智能体的研究表明，由于环境场景有限或复杂任务表现不佳，其韧性极低。我们探索了多种策略，使LLM作为智能体在流行的开源软件（OSS）智能家居自动化框架HomeAssistant中运行，以提升整体智能家居的韧性。我们的方法将传统监督学习技术和优化提示（prompting）作为核心学习过程。我们在优化流程中使用了涵盖不同推理水平和成本的一组多样化LLM，并在智能家居基准测试中最难任务的一个子集上评估其性能。我们纳入了ReAct和Reflexion智能体范式，并揭示出与针对HomeAssistant内多设备控制进行微调的LLM相比，这两种范式带来的投资回报边际，但在故障响应等韧性任务中显示出潜力。
英文摘要
Smart homes and smart devices are becoming more prevalent across millions of homes around the world. With the rise of AI, the smart home industry is quickly increasing its integration to manage common smart home tasks. However, existing work in large language models (LLMs) as agents within smart homes have shown minimal resilience due to limited environment scenarios or poor performance in complex tasks. We explore several strategies for LLMs as agents within the popular open-source software (OSS) smart home automation framework HomeAssistant to increase overall smart home resilience. Our approach combines traditional supervised learning techniques and optimized prompting as the core learning process. We use a diverse set of LLMs covering different levels of reasoning and costs in our optimization pipeline and evaluate their performance on a subset of the hardest tasks in a smart home benchmark. We include ReAct and Reflexion agentic paradigms and reveal how both provide marginal return on investment compared to fine-tuned LLMs for multi-device control within HomeAssistant but show promise in resilience tasks such as failure response.
CommentsPre-print
Journal refProceedings of the 2026 International Conference on Smart Energy Systems and Technologies (SEST)
DOI：10.1109/SEST67798.2026.11712302
