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

Bassam Adnan, Sathvika Miryala, Aneesh Sambu, Karthik Vaidhyanathan, Martina De Sanctis, Romina Spalazzese

Abstract: IoT systems face significant challenges adapting to user needs, often under-specified and evolving with changing environmental contexts. To address these complexities, users should be able to explore possibilities. At the same time, IoT systems must learn and support users in 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 is a realization of IoT-Together by integrating Large Language Models (LLMs) into its architecture. The presented work enables intelligent goal interpretation through a three-pass dialogue framework and dynamic IoT systems generation 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 evaluated the system performance using agent-based simulation and user studies. Results indicate efficient and accurate service identification and high adaptation quality. The empirical evidence indicates that integrating Large Language Models (LLMs) into IoT architectures can significantly enhance the architectural adaptability of the system while ensuring real-world usability.

External IDs:dblp:conf/icsa/AdnanMSVSS25