Abstract
Large programming courses often use test-driven autograding systems (e.g., CodeRunner) for instant feedback, but these usually only show which tests failed without explaining why or how to fix the error. Novice students struggle with such minimal guidance and often resort to trial-and-error. Meanwhile, AI coding assistants (e.g., GitHub Copilot, ChatGPT) can provide hints and code suggestions, but novices may over-trust these outputs and lack the skills to verify them. To solve these issues, we present TraceMate, an IDE plugin that pairs the autograder’s tests with a conversational AI chatbot. TraceMate augments test feedback with context-aware explanations and inline suggestions for code modifications, and immediately validates each AI suggestion on the test suite. This workflow gives actionable hints while ensuring any AI-proposed changes are correct. In a user study with novice programmers, participants using TraceMate solved problems more effectively and reported higher confidence than those using only the autograder. These results suggest that pairing automated tests with an interactive AI assistant can enhance learning in introductory programming courses.
| Original language | English |
|---|---|
| Title of host publication | VL/HCC 2025 - The IEEE Symposium on Visual Languages and Human-Centric Computing |
| Publisher | IEEE Computer Science Society |
| Number of pages | 7 |
| Publication status | Accepted/In press - 19 Jul 2025 |
| Event | The 2025 IEEE Symposium on Visual Languages and Human-Centric Computing - Raleigh, United States Duration: 7 Oct 2025 → 10 Oct 2025 Conference number: 41 https://conf.researchr.org/home/vlhcc-2025 |
Conference
| Conference | The 2025 IEEE Symposium on Visual Languages and Human-Centric Computing |
|---|---|
| Abbreviated title | VL/HCC 2025 |
| Country/Territory | United States |
| City | Raleigh |
| Period | 7/10/25 → 10/10/25 |
| Internet address |
Fingerprint
Dive into the research topics of 'TraceMate: Collaborating with AI in Test-Driven Programming'. Together they form a unique fingerprint.Projects
- 2 Active
-
Identification of at-risk students based on learning analytics: a Machine Learning approach
Selig, T. (PI), Purwanto, E. (CoPI) & Zhang, Q. (CoPI)
1/03/24 → 28/02/27
Project: Internal Research Project
-
Improving Accuracy of Medical Image Segmentation through Image Preprocessing, Data Augmentation and Information Embedding
Purwanto, E. (PI)
1/01/23 → 30/06/26
Project: Internal Research Project
Activities
- 1 Master Dissertation Supervision
-
AI for formative feedback in large computer programming courses
Selig, T. (Supervisor)
Jan 2025 → Jun 2026Activity: Supervision › Master Dissertation Supervision
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver