CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education

2025-07-18

AI Summary

Current LLM-based programming education approaches suffer from three key limitations: insufficient assessment of learners’ coding competencies, lack of personalized learning path planning, and inadequate deep, interactive tutoring—further constrained by monolithic agent architectures that struggle to comprehend complex codebases or deliver progressive instruction. To address these, we propose a multi-agent collaborative framework featuring dynamic task allocation, tightly integrated with code execution, debugging, and learning analytics tools. This enables adaptive learning path generation, real-time Q&A, stepwise scaffolding, and closed-loop feedback. Our core contributions are: (1) a dynamic coordination mechanism among functionally heterogeneous agents, and (2) a learning-state model grounded in programming competency progression, coupled with adaptive intervention policies. Empirical evaluation demonstrates statistically significant improvements in students’ programming proficiency, outperforming both static-content and single-agent baselines.

Technology Category

• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students' abilities, design learning plans, provide personalized material aligned with individual learning goals, and enable interactive learning. Current work mostly uses single LLM agents, which limits their ability to understand complex code repositories and schedule step-by-step tutoring. Recent research has shown that multi-agent LLMs can collaborate to solve complicated problems in various domains like software engineering, but their potential in the field of education remains unexplored. In this work, we introduce CodeEdu, an innovative multi-agent collaborative platform that combines LLMs with tool use to provide proactive and personalized education in coding. Unlike static pipelines, CodeEdu dynamically allocates agents and tasks to meet student needs. Various agents in CodeEdu undertake certain functions specifically, including task planning, personalized material generation, real-time QA, step-by-step tutoring, code execution, debugging, and learning report generation, facilitated with extensive external tools to improve task efficiency. Automated evaluations reveal that CodeEdu substantially enhances students' coding performance.

Problem

• Assess student abilities and design learning plans
• Provide personalized coding education materials
• Enable interactive multi-agent tutoring and debugging

Innovation

• Multi-agent LLMs for personalized coding education
• Dynamic agent-task allocation for student needs
• External tools integration for task efficiency