Strategies for LLM-Driven User Interface Generation in Smart Systems: A Comparative Analysis with Decision Guidance
Authors:
- Taras LypakTLTaras Lypak
- Halyna LypakHLHalyna Lypak
- Taras KramarTKTaras Kramar
- Oleksij DudaODOleksij Duda
Open Access
- 26 May 2026
- journal article
- Published by Ternopil Ivan Puluj National Technical University in Scientific journal of the Ternopil national technical university
- Vol. 122 (2) , 70-83
Abstract
Large language models (LLM) provide opportunities to generate user interfaces directly from natural-language intent, but the emerging generative-UI literature remains focused primarily on web and chat contexts rather than smart systems. Smart-system interfaces are characterized by stricter demands, necessitating grounding in concrete device registries, validation against real-world action consequences, and explainability to non-developer users. This paper identifies and compares six distinct strategies currently used for LLM-driven UI generation (direct structured-output prompting, template-augmented generation, retrieval-augmented generation, model-driven hybrid pipelines, constrained generation, and multi-agent decomposition) using criteria tailored to smart-system contexts: output consistency, safety and accuracy validation, explainability, latency, implementation complexity, generalisability, and failure handling. The comparison is then adapted to three representative domains: smart-home consumer IoT, smart industrial supervisory control, and smart cultural heritage (virtual and AR museums, AI-assisted reconstruction interfaces, and smart exhibit displays). For each domain, a primary strategy is recommended, modifications required to meet specific domain constraints are demonstrated, and an adapted reference architecture is presented. A decision matrix and a selection flowchart are developed to guide the selection of an LLM-based UI generation strategy for specific smart-system deployments. The paper closes by outlining several open challenges, including the verification of accuracy-critical generated interfaces and the integration of static generation with runtime adaptation.Keywords
This publication has 18 references indexed in Scilit:
- Control Industrial Automation System with Large Language Model Agents2025
- AdaptUI: A Framework for the development of Adaptive User Interfaces in Smart Product-Service SystemsUser Modeling and User-Adapted Interaction, 2024
- A conversational agent for creating automations exploiting large language modelsPersonal and Ubiquitous Computing, 2024
- "We Need Structured Output": Towards User-centered Constraints on Large Language Model Output2024
- LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems2024
- SashaProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2024
- An Information System Project Using Augmented Reality for a Small Local History Museum2023
- Adapting User Interfaces with Model-based Reinforcement Learning2021
- Guidelines for Human-AI Interaction2019
- A Unifying Reference Framework for multi-target user interfacesInteracting with Computers, 2003