Artificial intelligence (AI) and natural language processing technologies have fuelled the growth of Pedagogical Conversational Agents (PCAs) with empathic conversational capabilities. However, no systematic literature review has explored the intersection between conversational agents, education and emotion. Therefore, this study aimed to outline the key aspects of designing, implementing and evaluating these agents. The data sources were empirical studies, including peer‐reviewed conference papers and journal articles, and the most recent publications, from the ACM Digital Library, IEEE Xplore, ProQuest, ScienceDirect, Scopus, SpringerLink, Taylor & Francis Online, Web of Science and Wiley Online Library. The remaining papers underwent a rigorous quality assessment. A filter study meeting the objective was based on keywords. Comparative analysis and synthesis of results were used to handle data and combine study outcomes. Out of 1162 search results, 13 studies were selected. The results indicate that agents promote dialogic learning, proficiency in knowledge domains, personalized feedback and empathic abilities as essential design principles. Most implementations employ a quantitative approach, and two variables are used for evaluation. Feedback types play a vital role in achieving positive results in learning performance and student perceptions. The main limitations and gaps are the time range for literature selection, the level of integration of the empathic field and the lack of a detailed development stage report. Moreover, future directions are the ethical implications of agents operating beyond scheduled learning times and the adoption of Responsible AI principles. In conclusion, this review provides a comprehensive framework of empathic PCAs, mostly in their evaluation. The systematic review registration number is osf.io/3xk6a . Practitioner notes: What is already known about this topic: Emotions play a pivotal role in shaping the interaction process, making it essential to consider them when designing methodological strategies or learning tools. Empathic Pedagogical Conversational Agents (PCAs) have emerged as a crucial approach for enhancing and personalizing the learning experience (24/7) for pupils and supporting human teachers in their teaching process. Despite the creation of numerous empathic PCAs, there is a scarcity of Systematic Literature Reviews (SLRs) on their application in the educational field, particularly concerning the integration of emotional abilities in combination with the competencies of each subject. What this paper adds: It offers new insights into the design principles underlying the integration of the empathic field. It reviews different approaches for incorporating students' prior knowledge in real time. It provides a comprehensive and up‐to‐date overview of the research designs used for implementation, including quantitative, qualitative and mixed methods. It examines the factors that influence the effectiveness of empathic PCA in teaching and learning. It evaluates the types of feedback that enhance the impact of the empathic field on learning outcomes. Implications for practice and/or policy: It is crucial to grasp the topics that this paper introduces in order to effectively integrate new learning tools into any context. Techno‐pedagogical designers seeking to gain insights into empathic PCAs will find immense value in this SLR, as it comprehensively covers each stage of the process. For future research endeavours, this study offers a wealth of ideas to draw upon, enabling researchers to address the challenges outlined and explore new avenues of investigation.

Despite advances in educational technology, the specific ways in which Generative Artificial Intelligence (GAI) and Large Language Models cater to learners’ nuanced cognitive and emotional needs are not fully understood. This mini-review methodically describes GAI’s practical implementations and limitations in meeting these needs. It included journal and conference papers from 2019 to 2024, focusing on empirical studies that employ GAI tools in educational contexts while addressing their practical utility and ethical considerations. The selection criteria excluded non-English studies, non-empirical research, and works published before 2019. From the dataset obtained from Scopus and Web of Science as of June 18, 2024, four significant studies were reviewed. These studies involved tools like ChatGPT and emphasized their effectiveness in boosting student engagement and emotional regulation through interactive learning environments with instant feedback. Nonetheless, the review reveals substantial deficiencies in GAI’s capacity to promote critical thinking and maintain response accuracy, potentially leading to learner confusion. Moreover, the ability of these tools to tailor learning experiences and offer emotional support remains limited, often not satisfying individual learner requirements. The findings from the included studies suggest limited generalizability beyond specific GAI versions, with studies being cross-sectional and involving small participant pools. Practical implications underscore the need to develop teaching strategies leveraging GAI to enhance critical thinking. There is also a need to improve the accuracy of GAI tools’ responses. Lastly, deep analysis of intervention approval is needed in cases where GAI does not meet acceptable error margins to mitigate potential negative impacts on learning experiences.

This study examines the influence of pedagogical agents on enhancing emotional engagement in higher education settings through the provision of cognitive and affective feedback. The research focuses on students in a collaborative “Database Systems and Design”, comparing the effects of feedback from a human teacher (control group) to those of an Affective Pedagogical Tutor (APT) (experimental group). Emotional engagement was measured through key positive emotions such as motivation, curiosity, optimism, confidence, and satisfaction, as well as the reduction in negative emotions like boredom, anger, insecurity, and anxiety. Results suggest that APT feedback was associated with higher levels of emotional engagement compared to teacher feedback. Cognitive feedback from the APT was perceived as supporting learning outcomes by offering detailed, task-specific guidance, while affective feedback further supported emotional regulation and positive emotional states. Students interacting with the APT reported feeling more motivated, curious, and optimistic, which contributed to sustained participation and greater confidence in their work. At the same time, boredom and anger were notably reduced in the experimental group. These findings illustrate the potential of affective pedagogical agents to complement educational experiences by fostering positive emotional states and mitigating barriers to engagement. By integrating affective and cognitive feedback, pedagogical agents can create more emotionally supportive and engaging learning environments, particularly in collaborative and complex academic tasks.

Identifying the physiological indicators of confidence can help illuminate core aspects of learners’ metacognition. Yet, little is known about the potential relationship between confidence and physiological arousal in collaborative and gameful learning contexts. This study examined whether non-specific Skin Conductance Responses (NS-SCRs) are associated with retrospective confidence in a collaborative entrepreneurship board game, and whether this link depends on the gameful learning phase. The study further examined whether retrospective confidence predicted perceived individual performance and team gameplay outcome. Data were collected from 87 university students, nested within 29 teams of three. NS-SCR frequency was calculated for the whole Gameful learning session and for each gameful learning phase. Linear mixed-effects models were estimated. The current findings showed that, considering the whole gameful learning session, higher NS-SCR frequency predicted lower confidence at the within-team level, whereas no relationship was observed at the between-team level. Considering the specific gameful learning phases, higher within-team NS-SCR frequency both during the tutorial and gameplay phases predicted lower confidence, whereas NS-SCR frequency during the pitch phase was not significantly related to confidence. In addition, retrospective confidence positively predicted perceived individual performance, but not the team gameplay outcome. These findings suggest that retrospective confidence in collaborative gameful learning reflects momentary physiological arousal and is aligned with learners’ appraisals of their own performance but does not track the team gameplay outcome. For practice, the results highlight the value of supporting learners during high-uncertainty phases and of using structured team reflection to build calibrated confidence.