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

arXiv: https://arxiv.org/abs/2603.24940 · HTML: https://mlsanity.com/paper/2603.24940/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 16 of its 41 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation with Knowledge Graphs for Customer Service Question Answering](https://mlsanity.com/paper/2404.17723/) (2024)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [Large Language Models in Education: Vision and Opportunities](https://mlsanity.com/paper/2311.13160/) (2023)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [Large Language Models (GPT) for automating feedback on programming assignments](https://mlsanity.com/paper/2307.00150/) (2023)
- [Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs Can Analyze Long Sequences Flawlessly](https://mlsanity.com/paper/2408.01866/) (2024)
- [CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors](https://mlsanity.com/paper/2406.13972/) (2024)
- [Feedback-Generation for Programming Exercises With GPT-4](https://mlsanity.com/paper/2403.04449/) (2024)
- [Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges](https://mlsanity.com/paper/2401.08664/) (2023)
- [CommunityKG-RAG: Leveraging Community Structures in Knowledge Graphs for Advanced Retrieval-Augmented Generation in Fact-Checking](https://mlsanity.com/paper/2408.08535/) (2024)
- [How to Build an Adaptive AI Tutor for Any Course Using Knowledge Graph-Enhanced Retrieval-Augmented Generation (KG-RAG)](https://mlsanity.com/paper/2311.17696/) (2023)
- [SPHERE: Scaling Personalized Feedback in Programming Classrooms with Structured Review of LLM Outputs](https://mlsanity.com/paper/2410.16513/) (2024)
- [Ontology-driven Reinforcement Learning for Personalized Student Support](https://mlsanity.com/paper/2407.10332/) (2024)
- [Development and Evaluation of Adaptive LearningSupport System Based on Ontology of MultipleProgramming Languages](https://mlsanity.com/paper/2507.19728/) (2025)
- [A Survey on Feedback Types in Automated Programming Assessment Systems](https://mlsanity.com/paper/2510.18923/) (2025)

## Built on by (most cited first, 1 of 1)

- [CODE-GEN: A Human-in-the-Loop RAG-Based Agentic AI System for Multiple-Choice Question Generation](https://mlsanity.com/paper/2604.03926/) (2026)

## Abstract (arXiv)

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 across three instructional modes; adaptive, Generative AI (GenAI), and hybrid GenAI-adaptive. An experimental study was conducted to compare the learning performance and perception of the learners, and the effectiveness of these three modes using four key log features derived from 4956 code submissions across all experimental groups. The analysis results show that learners receiving feedback from GenAI modes had significantly more correct code and fewer code submissions missing essential programming logic than those receiving feedback from adaptive mode. In particular, the hybrid GenAI-adaptive mode achieved the highest number of correct submissions and the fewest incorrect or incomplete attempts, outperforming both the adaptive-only and GenAI-only modes. Questionnaire responses further indicated that GenAI-generated feedback was widely perceived as helpful, while all modes were rated positively for ease of use and usefulness. These results suggest that the hybrid GenAI-adaptive mode outperforms the other two modes across all measured log features.