# From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education

arXiv: https://arxiv.org/abs/2512.20714 · HTML: https://mlsanity.com/paper/2512.20714/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 149 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers](https://mlsanity.com/paper/2405.17739/) (2024)
- [A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education](https://mlsanity.com/paper/2312.03173/) (2023)
- [Large Language Models for Education: A Survey](https://mlsanity.com/paper/2405.13001/) (2024)
- [Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation](https://mlsanity.com/paper/2310.03780/) (2023)
- [Grade Like a Human: Rethinking Automated Assessment with Large Language Models](https://mlsanity.com/paper/2405.19694/) (2024)
- [CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors](https://mlsanity.com/paper/2406.13972/) (2024)
- [Improving Automated Code Reviews: Learning from Experience](https://mlsanity.com/paper/2402.03777/) (2024)
- [Evaluating Contextually Personalized Programming Exercises Created with Generative AI](https://mlsanity.com/paper/2407.11994/) (2024)
- [CodeTailor: LLM-Powered Personalized Parsons Puzzles for Engaging Support While Learning Programming](https://mlsanity.com/paper/2401.12125/) (2024)
- [Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework Support](https://mlsanity.com/paper/2412.11995/) (2024)
- [How Do Programming Students Use Generative AI?](https://mlsanity.com/paper/2501.10091/) (2025)
- [Iris: An AI-Driven Virtual Tutor For Computer Science Education](https://mlsanity.com/paper/2405.08008/) (2024)
- [61A Bot Report: AI Assistants in CS1 Save Students Homework Time and Reduce Demands on Staff. (Now What?)](https://mlsanity.com/paper/2406.05600/) (2024)
- [Evaluating Large Language Models for Code Review](https://mlsanity.com/paper/2505.20206/) (2025)
- [Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming](https://mlsanity.com/paper/2411.09261/) (2024)
- [Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study](https://mlsanity.com/paper/2508.08314/) (2025)
- [Automating Personalized Parsons Problems with Customized Contexts and Concepts](https://mlsanity.com/paper/2404.10990/) (2024)
- [EvoGPT: Leveraging LLM-Driven Seed Diversity to Improve Search-Based Test Suite Generation](https://mlsanity.com/paper/2505.12424/) (2025)
- [Assessing the Reliability and Validity of Large Language Models for Automated Assessment of Student Essays in Higher Education](https://mlsanity.com/paper/2508.02442/) (2025)
- [Pensieve Discuss: Scalable Small-Group CS Tutoring System with AI](https://mlsanity.com/paper/2407.17007/) (2024)

## Abstract (arXiv)

Generative AI enables personalized computer science education at scale, yet questions remain about whether such personalization supports or undermines learning. This scoping review synthesizes 32 studies (2023-2025) purposively sampled from 259 records to map personalization mechanisms and effectiveness signals in higher-education computer science contexts. We identify five application domains: intelligent tutoring, personalized materials, formative feedback, AI-augmented assessment, and code review, and analyze how design choices shape learning outcomes. Designs incorporating explanation-first guidance, solution withholding, graduated hint ladders, and artifact grounding (student code, tests, and rubrics) consistently show more positive learning processes than unconstrained chat interfaces. Successful implementations share four patterns: context-aware tutoring anchored in student artifacts, multi-level hint structures requiring reflection, composition with traditional CS infrastructure (autograders and rubrics), and human-in-the-loop quality assurance. We propose an exploration-first adoption framework emphasizing piloting, instrumentation, learning-preserving defaults, and evidence-based scaling. Recurrent risks include academic integrity, privacy, bias and equity, and over-reliance, and we pair these with operational mitigation. The evidence supports generative AI as a mechanism for precision scaffolding when embedded in audit-ready workflows that preserve productive struggle while scaling personalized support.