Designing artificial intelligence chatbots for self-regulated learning from a systematic review based on Habermas's three interests

Self-regulated learning (SRL) is widely acknowledged as a key driver of academic success and lifelong learning, yet learners often struggle to plan, monitor, and reflect effectively on their progress. Concurrently, advances in artificial intelligence (AI) chatbots offer unprecedented opportunities to scale SRL. This paper reviews 78 studies from 2018 to 2025 on how AI chatbots can be created to support self-regulated learning (SRL) by leveraging technology, social interaction, and reflection, based on Habermas's three types of knowledge interests (technical, practical, and emancipatory). We identify eight core chatbot functions that align with the forethought, performance, and self-reflection phases of Zimmerman's SRL cycle. Socially, effective implementations embed chatbots within teacher–peer–chatbot triads to facilitate co-regulation, dialogue, and community building. Critically, chatbots can prompt deep self-evaluation and ethical inquiry, though designs must guard against overreliance and superficial reflection. We synthesise these findings into an integrative framework that maps chatbot features onto SRL processes and Habermasian interests, and we highlight underexplored areas – such as K-12 contexts, multimodal analytics, and emancipatory reflection – for future research. Our review offers actionable guidance for researchers, designers, and educators seeking to harness AI chatbots as versatile partners in fostering autonomous, socially grounded, and critically reflective learners.