Advances in Knowledge-Based and LLM-Driven Systems for Mobile App Development

Mobile application development (MAD) is undergoing a transformative shift, driven by the need to adapt to diverse platforms, dynamic frameworks, and evolving user demands. Recent advancements in machine learning (ML), particularly through large language models (LLMs), generative AI, and knowledge-based systems, have unlocked new possibilities for creating intelligent, context-aware, and scalable solutions in MAD. This Research Topic seeks to showcase pioneering research at the intersection of ML, generative models, and hybrid AI architectures, with a focus on their application to enhance MAD processes.

Our objective is to explore how cutting-edge ML techniques—combined with knowledge representation, ontologies, and hybrid AI systems—can drive algorithmic innovation and deliver adaptive, data-driven solutions for MAD. We invite submissions that emphasize novel ML methodologies, generative approaches, and hybrid frameworks that address developers’ challenges, such as personalized recommendations, semantic understanding, and optimized development workflows. Contributions should highlight how these advancements push the boundaries of AI-driven innovation in MAD, aligning with the core themes of the "Machine Learning and Artificial Intelligence" domain.

We welcome original research articles and case studies that advance the field of ML and AI in MAD, including but not limited to:

• ML-Powered Recommender Systems Enhanced by LLMs for MAD.
• Knowledge Representation Using Ontologies and Generative AI Models.
• Algorithmic Innovations in Semantic Query Expansion and Intelligent Retrieval.
• Adaptive User Profiling with Temporal ML Model Evolution.
• Generative LLM Interfaces for Natural Language-Driven MAD Tools.
• Hybrid AI Frameworks Integrating ML and Knowledge-Based Systems for Code Analysis and Optimization.
• Novel ML-Driven Approaches for Automated Debugging and Workflow Enhancement in MAD.
• Evaluation of Generative Models and Hybrid Architectures in Real-World MAD Scenarios.