Date
Publisher
arXiv
The application of advanced generative artificial intelligence in education
is often constrained by the lack of real-time adaptability, personalization,
and reliability of the content. To address these challenges, we propose
ExpertAgent - an intelligent agent framework designed for personalized
education that provides reliable knowledge and enables highly adaptive learning
experiences. Therefore, we developed ExpertAgent, an innovative learning agent
that provides users with a proactive and personalized learning experience.
ExpertAgent dynamic planning of the learning content and strategy based on a
continuously updated student model. Therefore, overcoming the limitations of
traditional static learning content to provide optimized teaching strategies
and learning experience in real time. All instructional content is grounded in
a validated curriculum repository, effectively reducing hallucination risks in
large language models and improving reliability and trustworthiness.
Study at a glance
- Question: Can an agent framework combining dynamic planning and retrieval-augmented generation improve personalized and trustworthy educational support?
- Setting and data: Internal user acceptance test with volunteer participants; specific location, dates, and sample size not stated in the paper.
- Method: System development and prototype evaluation using a User Acceptance Model survey on a Likert scale.
Why it matters
Generative AI applications in education often lack real-time adaptability, deep personalization, and factual reliability. Addressing risks like model hallucinations and superficial adaptations is critical for responsible and trustworthy educational adoption.
Key findings
- Volunteer participants rated performance expectancy highest at 4.33 on a Likert scale, indicating the system could improve learning efficiency.
- Effort expectancy and facilitating conditions both scored 4.22, showing that participants found the system easy to use with adequate support.
- Social influence received a noticeably lower score of 2.78, indicating limited external driving factors such as peer recommendation or organizational support.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
