Test-Driven, AI-Assisted Learning: Replacing Lectures with Weekly Closed-Book Tests

2026-06-22

AI Summary

This study addresses the limitations of traditional lecture-based instruction in advanced theoretical courses, which often fails to foster active learning and lacks effective feedback mechanisms. The authors propose a novel pedagogical model that replaces conventional lectures with frequent closed-book assessments and AI agent–supported self-directed learning pathways. Weekly quizzes reinforce individual accountability, while AI systems automatically generate instructional content, assessment items, and grading feedback. The integration of version control ensures full reproducibility of the teaching workflow. Empirical implementation demonstrates that students widely perceive the quizzes as an effective accountability mechanism, and the AI infrastructure enables sustainable high-frequency evaluation at scale. The project code has been open-sourced, offering a reusable design pattern that establishes a new paradigm for delivering large-scale, high-quality education.

Abstract

This paper is an experience report on a 13-week Test-Driven, AI-Assisted (TDAA) redesign of DSAA 3071, Theory of Computation, an upper-level course at the Hong Kong University of Science and Technology (Guangzhou). The design is simple: the course replaces lectures with self-directed, AI-assisted learning, and frequent, independently completed tests create a high-frequency quality gate. AI agents help the instructor prepare the learning path, course website, tests, grading workflow, and repairs. Two conditions made this strict gate workable. Students needed a visible preparation path of learning sheets and aligned validation practice, so the closed-book tests felt fair rather than arbitrary. The instructor needed an AI-assisted materials harness, a version-controlled agent workspace, so that weekly drafting, review, test production, and grading could scale with human oversight. Evidence from a student survey ($N=18$), weekly scores, and the project's git history suggests that students treated the tests as useful accountability and that the harness made frequent closed-book testing operational. The evidence is limited to one small, proof-heavy course without a control group. The contribution is therefore a reusable design pattern: high-frequency tests preserve individual accountability, while AI agents make material production and marking scalable. We release the harness as a public starter template so that other instructors can reproduce it.

Problem

• test-driven learning
• AI-assisted education
• closed-book testing
• individual accountability
• lecture replacement

Innovation

• Test-Driven Learning
• AI-Assisted Education
• Closed-Book Testing
• Scalable Assessment
• AI Teaching Harness