Operating Systems (OS) courses are among the most challenging in computer science education due to the complexity of internal structures and the diversity of running environments. Traditional teaching methods often fail to address the diverse backgrounds, learning speeds, and practical needs of students. To tackle these challenges, we present SortingHat, a personalized digital teaching assistant tailored specifically for OS education. SortingHat integrates advanced AI technologies, including a retrieval augmented generation (RAG) framework and multi agent reinforcement learning (MARL), to deliver adaptive, scalable, and effective educational support. SortingHat features a 3D digital human interface powered by large language models (LLMs) to provide personalized, empathetic, and context aware guidance. It generates tailored exercises based on each student's learning history and academic performance, reinforcing weak areas and challenging advanced concepts. Additionally, the system incorporates a robust evaluation pipeline that ensures fair, consistent, and unbiased grading of student submissions while delivering personalized, actionable feedback for improvement. By combining personalized guidance, adaptive content creation, and automated assessment, SortingHat transforms OS education into an engaging, immersive, and scalable experience.
Figures & tables
Figure 1. SortingHat Structures
Figure 2. Customed Digital Assistant Generation
Figure 3. The multi-agent workflow for tailored exercise generation involves selecting suitable materials based on the student’s profile and a multi-agent discussion workflow to create customized exercises.
Figure 4. Process of Evaluation: Long submissions are divided into smaller, manageable sections for efficient processing. Agents, augmented with additional knowledge resources, engage in collaborative discussions to ensure an accurate evaluation. The feedback generator integrates the student’s academic level and historical submissions to produce personalized and contextually relevant feedback.
Figure 5. Digital Human TA offering personalized guidance while considering the academic level of students
Figure 6. An Example of Exercise Generation based on Students Academic Level:① concludes student’s academic level while ② generate corresponding exercise.
Figure 7. An Example of Weekly Posts about OS Advancement
Figure 8. An Example of Evaluating a Submission:① demonstrates how SortingHat provides personalized feedback tailored to the student’s academic level and submission history, while ② highlights its ability to deliver a comprehensive evaluation, ensuring both depth and accuracy in the assessment.
Figure 9. Distribution of Evaluation Scores for Submissions Evaluated 100 Times
Agentic Artificial Intelligence (AI) represents a paradigm shift from reactive systems to proactive, autonomous decision making frameworks. Existing AI-based educational systems remain fragmented and lack multi-level integration across stakeholders. This paper proposes the Agentic Unified Student Support System (AUSS), a novel multi-agent architecture integrating student-level personalization, educator-level automation, and institutional-level intelligence. The framework leverages Large Language Models (LLMs), reinforcement learning, predictive analytics, and rule-based reasoning. Experimental results demonstrate improvements in recommendation accuracy (92.4%), grading efficiency (94.1%), and dropout prediction (F1-score: 89.5%). The proposed system enables scalable, adaptive, and intelligent educational ecosystems.
Arya Mary K J, Deepthy K Bhaskar, Sinu T S +1
Department of Computer Engg, Govt. Model Engineering College,APJ Abdul Kalam Technological University, Kerala, India.
AI-driven education platforms have made some progress in personalisation, yet most remain constrained to static adaptation--predefined quizzes, uniform pacing, or generic feedback--limiting their ability to respond to learners' evolving understanding. This shortfall highlights the need for systems that are both context-aware and adaptive in real time. We introduce PAL (Personal Adaptive Learner), an AI-powered platform that transforms lecture videos into interactive learning experiences. PAL continuously analyzes multimodal lecture content and dynamically engages learners through questions of varying difficulty, adjusting to their responses as the lesson unfolds. At the end of a session, PAL generates a personalized summary that reinforces key concepts while tailoring examples to the learner's interests. By uniting multimodal content analysis with adaptive decision-making, PAL contributes a novel framework for responsive digital learning. Our work demonstrates how AI can move beyond static personalization toward real-time, individualized support, addressing a core challenge in AI-enabled education.
Megha Chakraborty, Darssan L. Eswaramoorthi, Madhur Thareja +5
Artificial Intelligence Institute, University of South Carolina
Educators face significant challenges in creating engaging, personalized assignments that accommodate students' diverse interests and cognitive abilities. Traditional one-size-fits-all assignments frequently lead to decreased student engagement and increased reliance on unethical practices such as plagiarism. To address these challenges, we present Taklif.AI, a platform that leverages Large Language Models (LLMs) to automatically generate personalized assignments tailored to individual student interests. Unlike existing AI-powered educational platforms that personalize based on academic performance metrics alone, Taklif.AI incorporates students' extracurricular interests and cultural contexts into the assignment generation process through a structured prompt engineering pipeline with input and output guardrails. The platform employs a serverless architecture on AWS with Next.js, using Llama 3.3 70B as the primary LLM via LiteLLM for multi-provider load balancing and LangChain for prompt orchestration. We describe the system architecture, the prompt design methodology, and the guardrails framework that ensures output quality. Preliminary user acceptance testing with 68 participants (65 students and 3 educators) indicates positive reception, with 84% of participants rating the personalization feature as beneficial. We discuss the platform's current capabilities and limitations, and outline directions for rigorous empirical evaluation of learning outcomes.
Zaki Kurdya, Mohammed Zuqlam, Salem Amassi +2
Faculty of Information Technology The Islamic University of Gaza Gaza, Palestine