rtificial intelligence is reshaping everyday life. In this revolution, the education sector is corrupted, creating new challenges for students and teachers alike. The current landscape of using artificial intelligence in education has pros and cons which must be considered. After assessing this scenario, our project materialized in developing a virtual tutor tailored to the recurrent needs. This tool is a complex artificial intelligence agent designed to be powered by specific academic material for the considered classes, and it aims to effectively support students’ education and help them prepare for the final assessment. This paper also discusses current limitations, including its position compared to more widely adopted artificial intelligence tools, highlighting the need for further refinements to improve its competitiveness. Although it is still under development, thanks to a survey used to quantify the evaluation of the tool in the first cohort of students, the preliminary results suggest that, with targeted improvements, the system could become a valuable academic tool.

AI-Driven Innovation in Higher Education: Developing, Implementing, and Assessing a Virtual Tutor

Elena Siletti;Alessandro Lanteri;Paola Pisano
2025-01-01

Abstract

rtificial intelligence is reshaping everyday life. In this revolution, the education sector is corrupted, creating new challenges for students and teachers alike. The current landscape of using artificial intelligence in education has pros and cons which must be considered. After assessing this scenario, our project materialized in developing a virtual tutor tailored to the recurrent needs. This tool is a complex artificial intelligence agent designed to be powered by specific academic material for the considered classes, and it aims to effectively support students’ education and help them prepare for the final assessment. This paper also discusses current limitations, including its position compared to more widely adopted artificial intelligence tools, highlighting the need for further refinements to improve its competitiveness. Although it is still under development, thanks to a survey used to quantify the evaluation of the tool in the first cohort of students, the preliminary results suggest that, with targeted improvements, the system could become a valuable academic tool.
2025
CARMA 2025 - 7th International Conference on Advanced Research Methods and Analytics
Roma
2-4 July 2025
CARMA 2025 Proceedings of the 7th International Conference on Advanced Research Methods and Analytics
Universitat Politècnica de València
134
141
https://ocs.editorial.upv.es/index.php/CARMA/CARMA2025/paper/viewFile/20529/10912
Artificial intelligence; Education; AI agent
Elena Siletti; Marta Casassa; Quawtar El Rhorfi; Alessandro Lanteri; Dario Pensa; Paola Pisano
File in questo prodotto:
File Dimensione Formato  
Casassa_etal_CARMA2025.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 1.64 MB
Formato Adobe PDF
1.64 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/2136883
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact