Multiagent AI Teaching Assistant for Personalization and Adaptive Programming Education

Programming education requires learners to develop conceptual understanding, problem-solving strategies, debugging skills, and the abilityto transfer knowledge to unfamiliar tasks. A single teaching pathway may not meet the needs of learners who differ in prior experience,pace, confidence, and preferred forms of explanation. This paper proposes a Multiagent AI Teaching Assistant that personalizesprogramming education by coordinating specialized agents for tutoring, code analysis, assessment, feedback, and learner modelling. Acoordinator combines learner goals and performance evidence to select the next activity, while a code-evaluation component examinessubmissions against tests and rubric criteria. The proposed system adapts explanations, hints, examples, and practice difficulty according toobserved learner needs. A feedback loop updates a learner profile after each activity and supports gradual progression from guided examplesto independent problem solving. The paper presents a conceptual 3D-style architecture diagram, a learning flowchart, functional modules,data entities, and a risk-aware evaluation plan. It emphasizes explainable recommendations, privacy, fairness, and human educatoroversight. The work is a proposed design rather than a report of a completed classroom experiment; therefore, no measured performanceimprovements are claimed. Future implementation should compare learning outcomes, task completion, debugging ability, learnerengagement, and teacher workload against a suitable baseline.