DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917354056712192 |
|---|---|
| author | Parvez, Nabiha Pallab, Tanvin Sarkar Imran, Mia Mohammad Zaman, Tarannum Shaila |
| author_facet | Parvez, Nabiha Pallab, Tanvin Sarkar Imran, Mia Mohammad Zaman, Tarannum Shaila |
| contents | Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitive programming offers a rich benchmark for such evaluation, given its diverse problem domains and strict efficiency requirements. We present an empirical study of LLM-based debugging on competitive programming problems and introduce DePro, a test-case driven approach that assists programmers by correcting existing code rather than generating new solutions. DePro combines brute-force reference generation, stress testing, and iterative LLM-guided refinement to identify and resolve errors efficiently.Experiments on 13 faulty user submissions from Codeforces demonstrate that DePro consistently produces correct solutions, reducing debugging attempts by up to 64% and debugging time by an average of 7.6 minutes per problem compared to human programmers and zero-shot LLM debugging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19399 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code Parvez, Nabiha Pallab, Tanvin Sarkar Imran, Mia Mohammad Zaman, Tarannum Shaila Software Engineering Debugging consumes a substantial portion of the software development lifecycle, yet the effectiveness of Large Language Models(LLMs) in this task is not well understood. Competitive programming offers a rich benchmark for such evaluation, given its diverse problem domains and strict efficiency requirements. We present an empirical study of LLM-based debugging on competitive programming problems and introduce DePro, a test-case driven approach that assists programmers by correcting existing code rather than generating new solutions. DePro combines brute-force reference generation, stress testing, and iterative LLM-guided refinement to identify and resolve errors efficiently.Experiments on 13 faulty user submissions from Codeforces demonstrate that DePro consistently produces correct solutions, reducing debugging attempts by up to 64% and debugging time by an average of 7.6 minutes per problem compared to human programmers and zero-shot LLM debugging. |
| title | DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2603.19399 |