Personalised adaptive learning is becoming increasingly popular as a method of providing each student on an online platform with learning experiences that are tailored to their own requirements and peculiarities. This enables learners to go along many learning routes with the shared objective of information and skill development. In such systems, adaptivity and intelligence play distinct roles, with adaptivity being a more data-driven decision-making approach and intelligence being the emulation of human traits in a learning setting. Pedagogical agents, as defined in the field of artificial intelligence, are virtual characters with anthropomorphic features that are introduced for educational reasons. Because e-learning is a continuously growing area, the responsibilities of pedagogical agents change based on the goals that have been established for them. This article provides a systematic evaluation of pedagogical agents’ research and empirical data in e-learning from 2015 to 2022. Their responsibilities will be examined specifically in terms of flexibility and variety, realistic simulation, and their influence on learning: performance improvement, improved motivation, and engagement. The article finishes with a discussion and recommendations on pedagogical agents’ future directions in this ever-changing world of individualised adaptive e-learning.

Personalisation in e-learning systems has become a major research area in recent times, as online learning is gradually evolving to become a major part of formal education. While there exist several learning management systems with a wide range of capabilities, one thing that remains inefficient is a standard framework for sharing knowledge across different platforms and, also, the inability of such systems to provide personalisation to the learning process by default. A large number of systems that have been implemented to provide personalisation apply few parameters and are course-specific; thus, flexibility, reusability, and scalability are greatly reduced. In this paper, we propose a framework for personalised learning, Weighted Agent System for Personalised E-learning Curriculum (WASPEC) implemented with Moodle, which is independent of the learning management system and provides the possibility of incorporating multiple personalisation parameters. This is accomplished with the combined use of web services, semantic web ontologies, and pedagogical agents, providing dynamic personalisation in the background of the e-learning system. This also provides added advantages of the possibility of sharing knowledge with other systems and reusability.

The ubiquity of smart devices and intelligent technologies embedded in e-learning settings fuels the drive to tackle the grand challenge of personalised adaptive learning. Personalised adaptive learning, which combines the core concepts of personalised learning and adaptive learning, attempts to take individual needs and features into account for personal development through adaptive adjustment. Personalised adaptive learning is supported at its heart by efficient real-time monitoring of the learning process and robust managerial capabilities, which are driven by data, as well as human intuition. The absence of reusable personalised content and logic is one of the key limitations of systems that adopt personalised learning. This is mostly due to the fact that business logic is frequently entangled with the system’s primary functionality. As a result, such systems are unable to interact with other systems that do not adhere to identical design standards. The application of modular frameworks and the semantic web has the potential to be leading technologies that foster reusable personalised content and systems that can efficiently share information. WASPEC, a modular framework for personalised adaptive learning, is evaluated in this paper. An improved architecture, WASPEC 2.0, ensuring more flexibility is also presented in the concluding sections.