APD-Agents: A Large Language Model-Driven Multi-Agents Collaborative Framework for Automated Page Design

2025-11-17

AI Summary

To address the time-consuming nature of mobile application page layout design, low team collaboration efficiency, and high tool learning overhead, this paper proposes a large language model (LLM)-driven multi-agent collaborative framework. The framework comprises five specialized agents—Orchestrator, SemanticParser, PrimaryLayout, TemplateRetrieval, and RecursiveComponent—that jointly perform semantic parsing, initial layout generation, template retrieval, and recursive component refinement. This enables end-to-end, high-fidelity, style-consistent layout generation directly from natural language specifications. Evaluated on the RICO dataset, our method achieves state-of-the-art performance in both layout plausibility and cross-page consistency. It significantly reduces manual intervention and inter-team coordination costs. By introducing a scalable, role-differentiated multi-agent paradigm, this work advances automated UI design and establishes a foundation for LLM-based, collaborative interface generation systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Teamwork
• Natural Language Processing: (Large) Language Models

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
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Layout design is a crucial step in developing mobile app pages. However, crafting satisfactory designs is time-intensive for designers: they need to consider which controls and content to present on the page, and then repeatedly adjust their size, position, and style for better aesthetics and structure. Although many design software can now help to perform these repetitive tasks, extensive training is needed to use them effectively. Moreover, collaborative design across app pages demands extra time to align standards and ensure consistent styling. In this work, we propose APD-agents, a large language model (LLM) driven multi-agent framework for automated page design in mobile applications. Our framework contains OrchestratorAgent, SemanticParserAgent, PrimaryLayoutAgent, TemplateRetrievalAgent, and RecursiveComponentAgent. Upon receiving the user's description of the page, the OrchestratorAgent can dynamically can direct other agents to accomplish users' design task. To be specific, the SemanticParserAgent is responsible for converting users' descriptions of page content into structured data. The PrimaryLayoutAgent can generate an initial coarse-grained layout of this page. The TemplateRetrievalAgent can fetch semantically relevant few-shot examples and enhance the quality of layout generation. Besides, a RecursiveComponentAgent can be used to decide how to recursively generate all the fine-grained sub-elements it contains for each element in the layout. Our work fully leverages the automatic collaboration capabilities of large-model-driven multi-agent systems. Experimental results on the RICO dataset show that our APD-agents achieve state-of-the-art performance.

Problem

• Automating mobile app page layout design to reduce manual effort
• Converting user descriptions into structured page designs automatically
• Enhancing layout quality through multi-agent collaboration and template retrieval

Innovation

• LLM-driven multi-agent framework automates mobile page design
• Dynamic agent collaboration converts descriptions to structured layouts
• Recursive component generation refines fine-grained design elements