Leveraging LLMs for Dynamic IoT Systems Generation through Mixed-Initiative Interaction

2025-02-02

AI Summary

To address the limited adaptability of IoT systems in scenarios characterized by ambiguous user requirements and dynamically evolving environments, this paper proposes a human–machine collaborative Mixed Interactive Intelligence (MII) framework that enables non-expert users—such as middle school students—to co-explore, co-define, and dynamically generate context-aware services. We pioneer the deep integration of large language models (LLMs) into IoT architectures to support multi-turn conversational goal understanding and runtime dynamic service composition. Furthermore, we introduce the IoT-Together augmentation paradigm, overcoming the adaptability bottlenecks inherent in rule-based, preconfigured systems. Evaluated through agent-based simulation and user studies in a smart tourism setting, our approach achieves a service identification and matching accuracy exceeding 92% and an average user satisfaction score of 4.7/5, demonstrating significant improvements in real-time system adaptability and practical usability.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Intelligent User Interfaces
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

IoT systems face significant challenges in adapting to user needs, which are often under-specified and evolve with changing environmental contexts. To address these complexities, users should be able to explore possibilities, while IoT systems must learn and support users in the process of providing proper services, e.g., to serve novel experiences. The IoT-Together paradigm aims to meet this demand through the Mixed-Initiative Interaction (MII) paradigm that facilitates a collaborative synergy between users and IoT systems, enabling the co-creation of intelligent and adaptive solutions that are precisely aligned with user-defined goals. This work advances IoT-Together by integrating Large Language Models (LLMs) into its architecture. Our approach enables intelligent goal interpretation through a multi-pass dialogue framework and dynamic service generation at runtime according to user needs. To demonstrate the efficacy of our methodology, we design and implement the system in the context of a smart city tourism case study. We evaluate the system's performance using agent-based simulation and user studies. Results indicate efficient and accurate service identification and high adaptation quality. The empirical evidence indicates that the integration of Large Language Models (LLMs) into IoT architectures can significantly enhance the architectural adaptability of the system while ensuring real-world usability.

Problem

• Internet of Things
• Adaptability
• User-Centered Design

Innovation

• Large Language Model Integration
• IoT-Together Enhancement
• Smart City Tourism Application