2026 ASEE Annual Conference & Exposition

Adaptive learning systems are emerging as powerful tools for creating personalized and data-driven learning environments in engineering education. These systems leverage artificial intelligence, learner modeling, and algorithmic feedback to adapt instructional content, pacing, and assessment to individual learner needs. While such systems have been widely promoted for enhancing engagement and conceptual mastery, the literature in engineering education remains fragmented. There is limited synthesis of how adaptive learning systems are conceptualized, designed, and evaluated within engineering contexts. This work-in-progress scoping review seeks to address this gap by systematically mapping the scope, focus, and methodological characteristics of adaptive learning systems in engineering education.

Guided by Arksey and O’Malley’s (2005) framework and PRISMA-ScR guidelines, this review draws from peer-reviewed studies retrieved across Scopus, Web of Science, ERIC, and IEEE Xplore. Search terms combined “adaptive learning systems,” “personalized instruction,” “AI-driven feedback,” and “engineering education.” Duplicate records were removed and abstracts screened using Ryan for systematic review management. Eligible articles are currently being coded in Excel for publication characteristics, adaptive mechanisms (rule-based, machine-learning, or learner-model-driven), instructional level, assessment design, and reported outcomes. Data extraction and inter-rater coding are ongoing.

This review is guided by the following research questions:
(RQ1) How are adaptive learning systems conceptualized, designed, and implemented in engineering education?
(RQ2) What types of learning outcomes and pedagogical benefits are reported from the use of adaptive learning systems?
(RQ3) What methodological and ethical considerations emerge in existing adaptive learning system research within engineering contexts?

Preliminary findings suggest that adaptive learning systems are most frequently implemented in large-enrollment foundational courses such as circuits, programming, and mechanics. Most systems focus on adaptive feedback and assessment mechanisms, while relatively few incorporate adaptive content sequencing or collaborative adaptation. Although reported outcomes are generally positive, methodological rigor varies widely. Longitudinal studies, transparent reporting of algorithms, and considerations of data ethics or learner privacy are rare.

Upon completion, this review will offer the first comprehensive synthesis of adaptive learning systems in engineering education. By integrating findings on design, implementation, and evaluation practices, the study aims to establish an evidence-informed framework to guide future development and research. Ultimately, this work contributes to the advancement of pedagogically grounded, ethically responsible, and scalable adaptive learning innovations in engineering education.