A Collaborative Multiagent Framework for Enhancing Learning in Object-Oriented Programming

Document Type

Conference Proceeding

Source of Publication

2026 17th Student Research Conference on Applied Computing Src 2026

Publication Date

4-22-2026

Abstract

This study evaluates a collaborative AI-Assisted multi-Agent learning environment designed to support the teaching of Object-Oriented Programming (OOP), focusing on inheritance. The environment integrates two specialized agents: A Concept Agent (Abs Agent) for theoretical scaffolding and a Code Agent (Rev Agent) for programming implementation support. Seventeen undergraduate students used the system to solve an inheritance-based task and completed a post-Activity evaluation survey.Results indicate high perceived usefulness for both agents, particularly in explaining abstract concepts, providing syntax assistance, and debugging code. The integration of both agents was rated positively, and the transition between conceptual explanation and coding support was effective. Students reported improvements primarily in conceptual understanding and implementation ability, alongside moderate to high confidence in solving conceptual and coding tasks independently.The findings suggest that a role-specialized multi-Agent architecture can effectively bridge conceptual and procedural knowledge in programming education while enhancing learner confidence.

ISBN

[9798319510167]

Publisher

IEEE

Disciplines

Computer Sciences | Education

Keywords

Chatbots, Education, Multi-Agents, Object-oriented programming

Scopus ID

105043107701

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS