Leveraging LLMs for Efficient and Personalized Smart Home Automation

TL;DR

This paper introduces IoTGPT, an LLM-based smart home agent that improves device control reliability, efficiency, and personalization by decomposing tasks, reusing subtasks, and adapting to user preferences, addressing key limitations of existing approaches.

Contribution

The paper presents IoTGPT, a novel LLM-based framework that enhances smart home automation through task decomposition, subtask reuse, and personalized adaptation, improving performance and user experience.

Findings

IoTGPT achieves higher accuracy than baselines.

It reduces latency and inference costs.

It enhances personalization and user satisfaction.

Abstract

The proliferation of smart home devices has increased the complexity of controlling and managing them, leading to user fatigue. In this context, large language models (LLMs) offer a promising solution by enabling natural-language interfaces for Internet of Things (IoT) control. However, existing LLM-based approaches suffer from unreliable and inefficient device control due to the non-deterministic nature of LLMs, high inference latency and cost, and limited personalization. To address these challenges, we present IoTGPT, an LLM-based smart home agent designed to execute IoT commands in a reliable, efficient, and personalized manner. Inspired by how humans manage complex tasks, IoTGPT decomposes user instructions into subtasks and memorizes them. By reusing learned subtasks, subsequent instructions can be processed more efficiently with fewer LLM calls, improving reliability and reducing both latency and cost. IoTGPT also supports fine-grained personalization by adapting individual subtasks to user preferences. Our evaluation demonstrates that IoTGPT outperforms baselines in accuracy, latency/cost, and personalization, while reducing user workload.