Leveraging LLMs for Efficient and Personalized Smart Home Automation

2026-01-08

arXiv.org

AI Summary

This work proposes IoTGPT, an intelligent agent designed to address the limitations of existing large language model (LLM)-based approaches for smart home control, which often suffer from low reliability, high latency, excessive computational cost, and insufficient personalization—factors that collectively increase user burden. IoTGPT introduces a novel human-like task decomposition and memory mechanism that breaks down user commands into reusable subtasks and adaptively tailors execution based on individual user preferences. By minimizing redundant LLM invocations, the method significantly reduces response latency and operational costs while maintaining high control accuracy. Furthermore, it enables fine-grained personalization, consistently outperforming current baseline methods across multiple evaluation metrics.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• smart home automation
• large language models
• user fatigue
• personalization
• device control

Innovation

• Large Language Models
• Smart Home Automation
• Task Decomposition
• Personalization
• Efficient Inference