Research

Paper

TESTING March 19, 2026

DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code

Authors

Nabiha Parvez, Tanvin Sarkar Pallab, Mia Mohammad Imran, Tarannum Shaila Zaman

Abstract

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.

Metadata

arXiv ID: 2603.19399
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-19
Fetched: 2026-03-23 16:54

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.19399v1</id>\n    <title>DePro: Understanding the Role of LLMs in Debugging Competitive Programming Code</title>\n    <updated>2026-03-19T18:46:34Z</updated>\n    <link href='https://arxiv.org/abs/2603.19399v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.19399v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <published>2026-03-19T18:46:34Z</published>\n    <arxiv:comment>This paper is accepted in FSE 2026 IVR track!</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Nabiha Parvez</name>\n    </author>\n    <author>\n      <name>Tanvin Sarkar Pallab</name>\n    </author>\n    <author>\n      <name>Mia Mohammad Imran</name>\n    </author>\n    <author>\n      <name>Tarannum Shaila Zaman</name>\n    </author>\n  </entry>"
}