Conference Agenda

This paper proposes a unified multi-agent reinforcement learning (MARL) framework for modelling pedagogical interaction in agent collectives, with explicit integration of task execution, emotional feedback, and consensus formation. The considered setting involves an agent-teacher, a robot–assistant, and a agent–student, where learning is achieved through imitation of motion–actions and evaluation communicated via motion–emotion primitives. Emotional states are modelled as discrete, observable signals that guide learning and social alignment rather than latent affective variables. The proposed framework is validated through a reproducible case study implemented in the Python Gymnasium environment. The agent–student is trained via policy optimization while the teacher and assistant follow scripted or parameterized policies, demonstrating how emotionencoded feedback can serve as an explicit learning signal in reinforcement learning. The results illustrate the feasibility of socially aligned learning in agent collectives and highlight the potential of emotion-informed MARL for educational robotics and human-centered multi-agent systems.

The growing number of STEM (Science, Technology, Engineering and Mathematics) learning resources created in schools should be collected in a virtual space with the possibility of use, reuse and adaptation to different learning scenarios. This will support teachers and students in realization of STEM educational practice. The aim of the paper is to present a lightweight software platform implemented through freely available cloud-based technologies to assist the STEM education in schools. The architectural solution is in accordance with performed requirement analysis regarding the functional features of the software, where teachers from different stages of secondary education are surveyed. Among the main functions are those related to management of STEM lessons and learning resources, organization of STEM courses, team working, implementation of synchronous and asynchronous communication, access to information board, built-in artificial intelligence support and training area for teachers to improve their competences in technology.

Here we present some results from a study involving the use of an intelligent tutor, based on a Large Language Model, in the educational context of two third-year classes in upper secondary school.
The tutor was intended as a support tool for learning, designed to guide students by means of a Socratic-style interaction.
In a first phase, a class received a training on Prompt Engineering (PE) and then used the tutor on the deepening learning activities about a topic, while the other class met the same activities without the tutor.
In the second phase, also the other class received the PE training and both classes used the tutor on a second subject.
We focus on the analysis of the final satisfaction questionnaire, aiming to see how students perceived the use of the tutor, across six perceptual dimensions.
Overall, the results show a positive and fairly consistent perception of the tutor's support, with perceived usefulness, instructional effectiveness, and conscious use of the tool showing slightly higher values, and lower values for engagement and metacognition.
These findings suggest a good level of acceptance of the tutor among students, alongside some room for improvement, particularly in terms of engagement.
The paper concludes with reflections on the integration of LLM-based tutors into everyday teaching practice, highlighting both opportunities and challenges observed during the study.

This study explores the sociodemographic, functional, and emotional profile of older adults who are frequent users of everyday digital technologies, with the aim of identifying the factors associated with digital inclusion and active ageing. The research was conducted using a quantitative design with a sample of 509 adults aged 60 and over residing in Castile and León (Spain). Data were collected through a 32-item Likert-type questionnaire designed to analyse patterns of digital technology use, the main motivations for use, and the emotional perceptions associated with its use.
The results reveal a differentiated profile of frequent users, primarily characterised by men aged between 60 and 70, with higher education, living in urban areas, not institutionalised, and with prior experience using digital devices during their working lives. Furthermore, the main uses are concentrated in communication, particularly through smartphones, social networks, and videoconferencing tools, while the primary motivations include improving daily convenience, information seeking, and learning. From an emotional perspective, the findings indicate a predominantly positive perception, highlighting emotions such as satisfaction, enjoyment, and a sense of personal achievement, alongside low levels of fear or frustration. These results suggest that digital inclusion in later life is closely linked to sociodemographic, experiential, and emotional variables, and they underscore the potential of digital technologies as tools for promoting social participation, well-being, and diversity in both learning contexts and everyday life.