Every smart home user interaction has an explicit or implicit goal. Existing home assistants easily achieve explicit goals, e.g., "turn on the light". In more natural communication, however, humans tend to describe implicit goals. We can, for example, ask someone to "make it cozy" rather than describe the specific steps involved. Current systems struggle with this ambiguity since it requires them to relate vague intent to specific devices. We approach this problem of flexibly achieving user goals from the perspective of general-purpose large language models (LLMs) trained on gigantic corpora and adapted to downstream tasks with remarkable flexibility. We explore the use of LLMs for controlling devices and creating automation routines to meet the implicit goals of user commands. In a user-focused study, we find that LLMs can reason creatively to achieve challenging goals, while also revealing gaps that diminish their usefulness. We address these gaps with Sasha: a system for creative, goal-oriented reasoning in smart homes. Sasha responds to commands like "make it cozy" or "help me sleep better" by executing plans to achieve user goals, e.g., setting a mood with available devices, or devising automation routines. We demonstrate Sasha in a real smart home.

翻译：摘要：每位智能家居用户的交互都蕴含显性或隐性目标。现有家庭助手能轻松实现显性目标（例如“开灯”），但在更自然的交流中，人类倾向于描述隐性目标。比如，我们可能要求对方“营造舒适氛围”而非描述具体步骤。当前系统难以应对这种模糊性——这要求系统将模糊意图关联至具体设备。本文从通用大型语言模型（LLM）的角度探索如何灵活实现用户目标——这类模型在大规模语料库上训练，并通过显著灵活性适应下游任务。我们研究了利用LLM控制设备并创建自动化程序以满足用户命令中隐性目标的可行性。通过以用户为中心的研究，发现LLM能通过创造性推理达成挑战性目标，但也暴露出削弱其实用性的缺陷。针对这些缺陷，我们提出Sasha：一种面向智能家居的创意目标导向推理系统。Sasha可响应“营造舒适氛围”或“帮助改善睡眠”等指令，通过执行方案（例如利用现有设备营造氛围或设计自动化程序）实现用户目标。我们在真实智能家居环境中完成了Sasha的演示验证。