Test-Driven, AI-Assisted Learning: Replacing Lectures with Weekly Closed-Book Tests
2026-06-22 • Computers and Society
Computers and Society
AI summaryⓘ
The authors describe their experience redesigning a college theory course to use frequent tests and AI tools instead of traditional lectures. Students learned mostly on their own with AI support and took many closed-book tests that helped keep them accountable. The instructor used AI to create learning materials, tests, and grading workflows more efficiently. Results show the approach worked well for this small group, but the authors note it was just one course without comparison groups. They provide their AI tools publicly so other teachers can try a similar setup.
Theory of ComputationTest-Driven LearningAI-Assisted EducationSelf-Directed LearningClosed-Book TestsFrequent TestingEducational TechnologyVersion ControlStudent AccountabilityCourse Design
Authors
Jin-Guo Liu, Shang-Qi Lu, Xin-Ran Shi, Long-Li Zheng, Wei Wang
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.