The digital transformation is leading to a constant change in qualification requirements, which means that personalized learning approaches are becoming increasingly important. Traditional education systems and learning platforms are often based on standardized content that is identical for all learners. As a result, they can only partially address individual differences in prior knowledge, learning strategies and motivation. This leads to inefficiencies in the learning process and can have a negative impact on motivation and learning success. One promising approach to overcoming these challenges is the use of generative artificial intelligence (AI) to dynamically adapt learning materials and paths based on individual learner profiles.

The landscape on digital learning systems currently shows various approaches that are mostly merging many different approaches like testing and gamification without personalization. To achieve a sustainable positive effect on the problems mentioned above, a holistic consideration of different personalization methods based on generative artificial intelligence (AI) is necessary.

This paper examines the integration of generative AI into personalized learning processes in vocational education and training (VET). Unlike conventional methods that only selectively adapt content, generative AI enables fully individualized creation of learning materials. Our research approach highlights various learner profile information, current state-of-the-art adaptation methods and their systemic integration before developing a comprehensive concept for the further development of personalization in the learning process. We analyze how comprehensive user data like prior knowledge, learning preferences, learning behavior, and motivation can be used to dynamically generate optimized learning content. This affects both the structure of the content and the form of presentation, for example through personalized analogies, interactive simulations, or adaptive difficulty levels.

We first provide a brief overview of the current state of research in the field of personalized learning systems and generative AI in vocational education and training. We then present our concept and look at the challenges and potential of this approach for the design of future-oriented learning processes. Finally, an outlook is given on possible further developments and the long-term effects of AI-supported personalization on VET systems.

Keywords: Personalized Learning, Generative AI, Vocational Education and Training.