MenuCraft: Interactive Menu System Design with Large Language Models

TL;DR

MenuCraft introduces an AI-assisted, dialogue-driven approach to menu design that leverages in-context learning from large language models to reduce data collection costs and avoid task-specific retraining. By framing menu design as an interactive collaboration between a human designer and an LLM, the paper demonstrates topic-based, command-based, and recommendation-oriented workflows, including hotkey assignment and tab naming, all via natural language prompts. The work highlights both the potential of LLMs to support diverse design tasks and the need for careful prompt design, user studies, and ethical considerations. Overall, MenuCraft represents a practical step toward integrating conversational AI into UI design workflows, with future work focusing on broader evaluation and cross-model generalization.

Abstract

Menu system design for user interfaces is a challenging task involving many design options and various human factors. For example, one crucial factor that designers need to consider is the semantic and systematic relation of menu commands. However, capturing these relations can be challenging due to limited available resources. Large language models can be helpful in this regard, using their pre-training knowledge to design and refine menu systems. In this paper, we propose MenuCraft, an AI-assisted designer for menu design that enables collaboration between the designer and a dialogue system to design menus. MenuCraft offers an interactive language-based menu design tool that simplifies the menu design process and enables easy customization of design options. MenuCraft supports a variety of interactions through dialog that allows performing in-context learning.