A Design Framework for Augmented Intelligent Reality (AIR) Systems in Language Learning

This paper presents a comprehensive design framework for Augmented Intelligent Reality (AIR) systems, which uniquely integrates augmented reality (AR) and generative artificial intelligence (AI) to facilitate immersive and personalised language learning experiences. The framework is grounded in established learning theories, including Constructivism, Self-Regulated Learning, Situated Learning, Cognitive Load Theory, and Social Constructivism, providing a solid theoretical foundation for its application. The AIR framework is designed to guide the development of interactive AR scenarios that AI-driven conversational agents complement. These agents serve as intelligent companions, engaging learners in meaningful dialogues and providing real-time feedback, essential for language acquisition. By fostering an environment where learners can practice language skills in contextualised settings, the framework emphasises the importance of learner engagement through various methods, such as personalised feedback, collaborative activities, and strategies to enhance motivation. The paper further discusses how each theoretical component is operationalised within system features, offering concrete examples of how pedagogical principles translate into practical design elements. Additionally, it proposes directions for future empirical validation, emphasising the need for research to assess the effectiveness of the AIR framework in real-world educational settings. This validation will help refine the framework and ensure its alignment with contemporary language learning needs, ultimately contributing to developing scalable, engaging, and effective AI-enhanced language learning environments.