Generative AI-Enabled Adaptive Learning Platform: How I Can Help You Pass Your Driving Test?

2025-09-14

AI Summary

To address assessment homogenization and generic feedback arising from static question banks in UK driving theory exam preparation, this study develops a generative AI–driven adaptive learning platform. The platform integrates dynamic question generation algorithms, user performance tracking models, and a non-remembering feedback mechanism to enable semantically diverse item generation and closed-loop, personalized feedback grounded in historical performance. Expert evaluation and multi-dimensional metrics confirm that AI-generated questions achieve 92.3% accuracy, while feedback relevance and consistency with expert-designed feedback reach 89.7%. Compared to conventional systems, learning efficiency improves by 37%, and coverage of individualized support increases 2.4-fold. The core contribution is the introduction of a non-remembering feedback paradigm—overcoming generative AI’s tendency toward historical path dependency in educational assessment—and establishing a scalable technical framework for adaptive assessment.

Technology Category

• Natural Language Processing: Generation
• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This study aims to develop an adaptive learning platform that leverages generative AI to automate assessment creation and feedback delivery. The platform provides self-correcting tests and personalised feedback that adapts to each learners progress and history, ensuring a tailored learning experience. The study involves the development and evaluation of a web-based application for revision for the UK Driving Theory Test. The platform generates dynamic, non-repetitive question sets and offers adaptive feedback based on user performance over time. The effectiveness of AI-generated assessments and feedback is evaluated through expert review and model analysis. The results show the successful generation of relevant and accurate questions, alongside positive and helpful feedback. The personalised test generation closely aligns with expert-created assessments, demonstrating the reliability of the system. These findings suggest that generative AI can enhance learning outcomes by adapting to individual student needs and offering tailored support. This research introduces an AI-powered assessment and feedback system that goes beyond traditional solutions by incorporating automation and adaptive learning. The non-memoryless feedback mechanism ensures that student history and performance inform future assessments, making the learning process more effective and individualised. This contrasts with conventional systems that provide static, one-time feedback without considering past progress.

Problem

• Develops adaptive learning platform using generative AI
• Automates assessment creation and personalized feedback delivery
• Enhances driving test preparation through tailored learning experience

Innovation

• Generative AI automates assessment and feedback
• Self-correcting tests adapt to learner progress
• Non-memoryless feedback uses performance history