2026· International Journal of Information and Education Technology· 0 citations· 40 references
TL;DR
Michael, a syllabus-aware AI teaching assistant designed to scaffold reasoning through structured, hint-first dialogue aligned with course progression, rather than providing direct solutions, is introduced, suggesting that curriculum-aligned constraints and hint-first scaffolding can support instructional integration without displacing pedagogical goals.
Abstract
The integration of Artificial Intelligence (AI) into higher education offers scalable support for students but raises concerns regarding over-reliance, reduced effort, and diminished deep learning. This study introduces Michael, a syllabus-aware AI teaching assistant designed to scaffold reasoning through structured, hint-first dialogue aligned with course progression, rather than providing direct solutions. The system was deployed in an undergraduate Structured Query Language (SQL) course across three consecutive semesters and evaluated using a mixed-methods design combining interaction logs, pre–post questionnaires (N = 170), and classroom observations. Results indicate high perceived ease of use (M = 4.43) and a moderate but statistically significant increase in trust following exposure (from M = 3.29 to M = 3.58), while AI self-efficacy showed only minor changes. Usage patterns revealed a bifurcated structure, with students engaging in both short troubleshooting interactions and extended tutoring dialogues. Qualitative findings highlight adoption waves, tensions between efficiency and depth, and the sensitivity of trust to system reliability. These findings suggest that curriculum-aligned constraints and hint-first scaffolding can support instructional integration without displacing pedagogical goals. Rather than demonstrating causal learning gains, this study contributes design principles and in-situ evidence for deploying domain-specific AI assistants in technical higher-education contexts.
Large language models (LLMs) are increasingly used as on-demand conversational learning assistants, but they typically do not adapt explanations to a student’s background unless explicitly prompted. We present the Personalized Learning Assistant Interface (PLAI), a web-based prototype that generates explanations from lecture slides, audio transcripts, and a structured student profile through a chat-based interface. We evaluated PLAI in a controlled pilot study with 24 STEM students, comparing profile-based personalization with a baseline condition using the same slide and transcript context. Immediate learning was assessed with a five-item knowledge test, while subjective experience was measured using the User Experience Questionnaire (UEQ) and open-ended feedback. We did not observe clear differences in knowledge-test outcomes, but participants in the personalized condition reported significantly higher UEQ Stimulation. These results suggest that profile-based multimodal prompts may mainly support motivational engagement rather than immediate test performance, while larger and longer-term studies are needed to assess learning effects.
Furkan Ali Yurdakul, Yiman Wu, Maria Torres Vega et al.· Message Understanding Confer...· 0 citations
EduMind is introduced, a unified tutoring and assessment platform designed around a dual-track evaluation model that demonstrates how assessment and tutoring can be unified into a seamless workflow, and remained operationally stable throughout all testing phases.
Dhyan Gowda, M. Aruna, P. Prasad et al.· International Journal of Sci...· 0 citations
Structured human-computer interactions with higher education chatbots to explore whether these chatbots were programmed to provide financial counseling to college students found that many systems marked as AI chatbots fell short of adaptive, generative capabilities which are the essence of AI systems.
Richard Simonds, Z. Taylor, Sara Ray· Journal of Ethics and Emergi...· 0 citations
Generative AI chatbots are increasingly used in introductory programming courses, but whether they support learning or encourage over-reliance remains unclear. To examine which interaction features are associated with productive persistence, we analyzed 198 CS1 student–chatbot conversation logs using a five-dimensional coding scheme: query type, response relevance, response type, dialogue outcome, and effectiveness marker. Persistence was measured as the number of student prompts per log. Negative binomial models showed that relevance failures predicted longer interactions, particularly false positives (IRR = 2.49) and false negatives (IRR = 1.65), both p < 0.001. Logistic models showed that false negatives strongly predicted unresolved sessions (OR = 9.94, p = 0.008), suggesting that the inability to answer accelerates abandonment. In contrast, conceptual (Socratic) responses predicted progressive effectiveness markers. Overall, interaction quality, not mere usage, appears to drive productive persistence, highlighting the importance of minimizing false negatives and encouraging Socratic scaffolding in educational chatbot design and deployment.
Rubaina Khan, Joshua Siderius, Kyle James Ross et al.· Proceedings of the Canadian...· 0 citations
HeuristicEdu is presented, a two-phase pipeline that aligns Qwen2.5-7B toward Socratic tutoring via supervised warm-up and Group Relative Policy Optimization (GRPO), and Scaffolding Effectiveness and Conversation Depth are introduced to evaluate outcomes beyond surface fluency.
Xiaokun Wang, Siyu Song, Wentao Liu et al.· arXiv.org· 0 citations
Generative social robots (GSRs) powered by large language models offer new possibilities for personalized tutoring in higher education, but also introduce risks related to misinformation, missing transparency, or reinforcing incorrect student responses. Prior work identified knowledge-based design (KBD) requirements that define the informational prerequisites for GSRs to manifest responsible and effective tutoring behavior in higher education. In this paper, we operationalized selected KBD requirements in the Reachy Mini robot platform through system prompting, retrieval-augmented generation, and stateful prompt orchestration. As a result, we present Teachy Mini, a GSR tutoring system that was developed using KBD. To test the system, we conducted a preliminary evaluation study. Participants (N = 24) completed a robot-guided learning session about research methodologies. They learned either with Teachy Mini or with a control version that did not follow KBD principles. Teachy Mini was perceived as significantly more aligned with responsible tutoring behavior than the control robot. Moreover, a manipulation check illustrated that Teachy Mini used personalization, slide-grounded explanations, Socratic questioning, affective support, and learner-anchored feedback more consistently than the control robot. No significant between-condition differences were found in system acceptance, intrinsic motivation, or learning effectiveness, although exploratory analyses suggested a positive effect of KBD on objective learning gains when accounting for learner preferences. Overall, the study offered an initial implementation and preliminary evaluation of KBD for GSR tutoring, indicating that KBD can shape responsible robot behavior and potentially increase learning effectiveness in robot-supported learning.
Stephan Vonschallen, Karim Kaufmann, Dominique Oberlé et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
