Developing self-regulated learning (SRL) skills among young adolescents is crucial for lifelong learning, and teachers play a vital role in fostering these skills. Problem-solving is a key SRL skill; however, both learners and teachers encounter challenges during the problem-solving process and in evaluating its incorporated strategies. To tackle these challenges, this study examined students’ problem-solving difficulties using a generic video-assisted SRL training programme, based on teachers’ reports, and analysed these challenges across STEM and non-STEM domains. This study focusses on identifying and classifying the difficulties of 241 students within the problem-solving framework, as reported by teachers across various disciplines and grades (6–11). The analysis revealed that the most significant difficulties arose during the problem identification, followed by time planning and management, problem exploration, solution development and solution evaluation. Specifically, STEM teachers reported relatively fewer difficulties in problem exploration than in other steps, while non-STEM teachers reported fewer challenges in presenting and communicating solutions to peers. A dedicated map named the problem-solving sort out setbacks (PS-SOS) map was created to pinpoint challenges within the problem-solving process. The application of this mapping technique can further support the development of technology-based feedback systems, including digital assistants, which offer valuable assistance to students.

Self-regulated learning (SRL) is crucial in today‟s educational landscape, championing students' autonomy over their learning journey. Yet, SRL, especially in problem-solving, poses significant difficulties for students. This study innovatively bridges this gap with a set of design principles for a generative AI chatbot specifically shaped to promote students' SRL skills during problem-solving tasks. Leveraging insights from feedback collected from both educators and students involved in a blended SRL program, this research shines a light on the range of difficulties involves in SRL within problem solving context. It pinpoints three main difficulties: Inconsistencies in assessment and perception that create a gap between student self-evaluations and educator assessments; Cognitive strategies difficulties that hinder skill application; and beyond cognitive difficulties such as motivation and task self-management obstacles toward independent learning. Responding to these difficulties, the design principles of the proposed AI chatbot are focused on providing structured guidance, which includes explicit instruction in cognitive and motivational skills, offering personalized feedback based on the specific difficulties, and facilitating the assessment of these skills during task performance. This approach not only advances the theoretical framework of SRL but also translates these concepts into tangible support mechanisms, equipping educators with an innovative tool to enhance SRL. The chatbot stands as a testament to the power of generative AI in transforming educational practices, paving the way for learners to become more self-reliant and adept in navigating the complexities of the digital learning era.

As education shifts toward student-centered learning, evaluating pre-service teachers' ability to foster self-regulated learning (SRL) is essential. This study examines lesson plans as performance-based assessment tools for evaluating pre-service teachers' competence in designing SRL-supportive instruction in online courses. Through qualitative analysis of 37 lesson plans created by 73 pre-service teachers, the research applies a three-dimensional analytical framework focusing on SRL strategy implementation, technology integration, and pedagogical competence. Findings reveal significant variability in how teachers structure SRL, scaffold autonomy development, and incorporate instructional technologies. High-quality lesson plans explicitly embedded metacognitive scaffolds and included structured support for student autonomy, while weaker plans provided inadequate SRL elements and lacked clear instructional rationales. Technology integration varied, with some lesson plans leveraging digital tools to enhance reflection and feedback, while others used technology in a passive, content-delivery manner. These findings reinforce the validity of lesson plans as assessment tools, offering teacher educators a structured alternative to self-reports in evaluating pre-service teachers' instructional reasoning and readiness to promote SRL in diverse learning environments.

Self-regulated learning (SRL) is required for learners of all ages and disciplines. There is a need for a variety of assessment tools to assess the professional knowledge of teachers in SRL and self-regulated teaching (SRT). Situational judgment tests (SJT) can serve as a measurable assessment tool for evaluating teachers' SRL and SRT knowledge. This research constitutes the second stage in the development of such an SJT tool dealing with the formulation of responses to scenarios created in the previous stage. Additionally, the introduction of GenAI-assisted evaluation poses the need to explore the still understudied human-GenAI interaction during assessment tools development. This study used thematic analysis for exploring the responses generated by GenAI (ChatGPT) and researchers for the previously formulated scenarios to examine the contribution of both agents in the tool development process. A main theme – standardization and patterning (GenAI) versus flexibility and openness (researchers) was found. The study highlights the potential of combining GenAI and researchers in developing assessment tools and the contribution of each.