Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system

📰 ArXiv cs.AI

Evaluating AI-based feedback and recommendations in a programming learning system using LLM and RAG

advanced Published 27 Mar 2026

Action Steps

Design a framework integrating LLM and RAG with a knowledge graph and user interaction history
Develop an adaptive learning support system to assess learners' code and generate formative feedback
Evaluate learner preferences and outcomes using the developed framework
Refine the system based on learner feedback and performance data

Who Needs to Know This

AI engineers and educators can benefit from this research to improve adaptive learning systems, while product managers can apply these findings to develop more effective learning tools

Key Insight

💡 Integrating LLM and RAG with a knowledge graph can enhance adaptive learning systems

Key Takeaways

Evaluating AI-based feedback and recommendations in a programming learning system using LLM and RAG

Full Article

Title: Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system

Abstract:
arXiv:2603.24940v1 Announce Type: cross Abstract: This paper introduces the design and development of a framework that integrates a large language model (LLM) with a retrieval-augmented generation (RAG) approach leveraging both a knowledge graph and user interaction history. The framework is incorporated into a previously developed adaptive learning support system to assess learners' code, generate formative feedback, and recommend exercises. Moerover, this study examines learner preferences acr

Read full paper → ← Back to Reads