TOPIC:
Agentic AI for Personalized Learning Path
Recommendations
STUDENT NAME [Link]
Adapa Soujanya 22KN1A6142
Internship Guide:
Cherukula Devi Deekshitha 23KN5A6101 Mr [Link]
Chunduri Venkata Ganesh 22KN1A6118 Chitti Babu
Kalli Tagore Avinash 22KN1A6158
Contents
• Introduction
• Literature Survey
• Existing Method
• Proposed Method
• Motivation
• Objectives
• System Block Diagram
• Architecture
• Expected Results
• Conclusion
• References
Add a footer 2
• Queries
FR
Introduction
Agentic AI refers to autonomous, goal‑based systems
that act intelligently to achieve predefined objectives.
In education, it enables personalized, adaptive
learning tailored to each student’s pace, strengths,
and preferences.
The proposed research focuses on evaluating such AI
systems for generating personalized learning path
recommendations, improving individual learning
outcomes and engagement.
Add a footer 3
FR
Literature Survey
• Pramod Babar (2025): “Agentic AI for Personalized Education
and Adaptive Learning Environments” — demonstrated
adaptive frameworks using multi‑ agent systems and LLMs.
• Luckin et al. (2025): AI in education facilitating continuous
assessment for personalization.
• Gera et al. (2025): Building Intelligent Learning Systems —
introduced layered architectures integrating reasoning agents
and emotional intelligence in learning workflows.These studies
show that agentic AI enhances adaptability and retention.
Add a footer 4
Motivation / Drawbacks in Existing
Methods
• Lack of continuous adaptation to student
progress.
• One‑size‑fits‑all content [Link]
emotional or contextual understanding.
• No proactive agent behavior — students must
initiate requests manually.
Add a footer 5
Proposed Method
• The proposed system applies agentic AI principles to
design a learning path recommender that
autonomously analyzes student data, predicts
next‑best lessons, and adapts difficulty based on
performance [Link] integrates:
• A student profile analyzer using progress and
engagement metrics.
• A goal‑oriented agent for intelligent
decision‑making.
• A content recommender module driven by
reinforcement learning and knowledge graphs.
Add a footer 6
FR
Objectives
• To evaluate the feasibility and accuracy of an agentic
AI‑based recommendation system.
• To compare personalized path generation against
traditional fixed learning models.
• To improve learner engagement and completion rates
through adaptive recommendations.
Add a footer 7
Architecture
Add a footer 8
FR
Block Diagram:
Add a footer 9
FR
Expected Results / Outcomes /
Sample Graphs
• 30 % increase in engagement through customized
recommendations.
• Improved learning‑path efficiency compared with
static methods.
• Expected outcomes measurable using metrics such as
personalization accuracy, completion time, and
satisfaction scores.
Add a footer 10
Conclusion
This project evaluates how agentic AI can intelligently
personalize learning paths, offering scalable, adaptive,
and accessible educational [Link] findings will
help refine future agent‑based learning tools and bridge
the gap between theoretical AI frameworks and
real‑world classroom applications.
Add a footer 11
FR
References
• Pramod A. Babar (2025), Agentic AI for
Personalized Education and Adaptive Learning
Environments, IJCE
• Rishiraj Gera (2025), Building Intelligent
Learning Systems: Agentic AI Workflows,
MagicEDTech
• XenonStack (2025), How AI Personalizes
Learning Paths
• UCL Knowledge Lab (2025), Agentic AI in
Personalized Learning
Add a footer 12
FR
Thank You
13
