Sasha：基于大语言模型的智能家居创造性目标导向推理
Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models
AI总结：
针对智能家居助手难以理解用户模糊目标类指令的问题，研究引入大语言模型，提出智能助手Sasha，通过用户研究验证其可响应宽松指令实现目标，同时也指出了相关局限。
摘要：
智能家居助手在用户指令直接且明确（例如“打开厨房灯”），或由硬编码例程指定响应时表现最佳。然而在更自然的交流中，人类的语言不受约束，通常描述目标（例如“让这里变得舒适”或“帮我节能”），而非指明具体的目标设备以及要对这些设备执行的操作。现有系统无法理解这些未明确指定的指令，因为它们无法结合人类的实际情境来推理设备与设置。我们将大语言模型（LLM）引入这一问题领域，探索其在智能家居响应用户未明确指定的指令时，用于控制设备和创建自动化例程的作用。我们通过一项覆盖不同年龄用户的调研，实证研究了LLM生成的行动计划的基线质量与失效模式。我们发现LLM能够进行创造性推理以实现有挑战性的目标，但也存在多种失效模式，降低了其实用性。我们推出了更智能的智能家居助手Sasha来解决这些不足。Sasha通过执行实现用户目标的计划来响应约束宽松的指令，比如“让这里舒适”或“帮我睡得更好”，例如利用可用设备营造氛围，或是设计自动化例程。我们通过一项实操用户研究实现并评估了Sasha，展示了由LLM驱动的智能家居在面对不受约束的用户生成场景时的能力与局限。
英文摘要：
Smart home assistants function best when user commands are direct and well-specified (e.g., "turn on the kitchen light"), or when a hard-coded routine specifies the response. In more natural communication, however, human speech is unconstrained, often describing goals (e.g., "make it cozy in here" or "help me save energy") rather than indicating specific target devices and actions to take on those devices. Current systems fail to understand these under-specified commands since they cannot reason about devices and settings as they relate to human situations. We introduce large language models (LLMs) to this problem space, exploring their use for controlling devices and creating automation routines in response to under-specified user commands in smart homes. We empirically study the baseline quality and failure modes of LLM-created action plans with a survey of age-diverse users. We find that LLMs can reason creatively to achieve challenging goals, but they experience patterns of failure that diminish their usefulness. We address these gaps with Sasha, a smarter smart home assistant. Sasha responds to loosely-constrained 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 implement and evaluate Sasha in a hands-on user study, showing the capabilities and limitations of LLM-driven smart homes when faced with unconstrained user-generated scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
