Agentic AI in Education: State of the Art and Future Directions
Open accessAbstract
Agentic AI systems are self-contained, goal-based entities designed to operate autonomously with little human intervention and dynamically respond to shifting contexts. This survey considers their transformative potential in education, ranging from intelligent tutoring systems and adaptive test-taking platforms to autonomous learning companions that can provide customized guidance and assistance. We provide an organized overview of the state of the field, classify existing and developing uses and assess their pedagogical worth, benefits and trade-offs. In the process, we also refer to such areas as learner motivation, equity, transparency and ethical concerns. Finally, we chart directions for future research and ethical implementation, highlighting how autonomous AI can reshape teaching, learning and educational spaces within the next several years.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
With the transition already underway to agentic AI, the authors anticipate that policies should and will shift as time progresses and institutions respond accordingly.
“Moreover, with the transition already underway to agentic AI [191], we anticipate that policies should and will shift as time progresses and institutions respond accordingly.”
From Navigating the Ethical and Societal Impacts of Generative AI in Higher Computing Education (2025) · cites this paper as [191]
Cited by
Sorted by citations
Navigating the Ethical and Societal Impacts of Generative AI in Higher Computing Education
Mak, J., Nakatumba-Nabende, J., Clear, T., Clear, A., Abluwi, I., Andrei, O., Angeli, L., MacNeil, S., Oyelere, S. S., Hale Rattigan, M., et al. (2025) · Proceedings of the 2025 Working Group Reports on Innovation and Technology in Computer Science Education · doi:10.1145/3760545.3783975 · Cited by 12 · see citing works
When Can AI Models Explain Learning? Validity Criteria for AI as Cognitive Models in Education
Wang, P., Viberg, O., Law, E. L.-C., & Greiff, S. (2026) · Educational Psychology Review · doi:10.1007/s10648-026-10202-y · Cited by 3 · see citing works
Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving
Sharif, M. T., & Rehman, A. (2026) · arXiv · doi:10.48550/arxiv.2606.05704
“Similarly, studies on agentic AI in education also note the growing importance of autonomous agents in education [10].”
- Authors
- Kostopoulos, G., Gkamas, V., Rigou, M., & Kotsiantis, S.
- Affiliations
- University of Patras (GR)
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 177467-177491
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4415125543
- Cited by
- 69
- References
- 0
- Citations by year
- 2026: 67 · 2025: 2
- FWCI
- 27.78
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- European Union in the Context of the Erasmus+ Project Generative AI Skills Academy (101179990)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- agentic AI, intelligent tutoring systems, personalized learning, student motivation, educational equity, AI transparency, AI ethics in education, future of teaching and learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
