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

TL;DR

This paper empirically evaluates the effectiveness of Large Language Models in debugging competitive programming code, introducing DePro, a test-case driven approach that significantly improves debugging efficiency.

Contribution

The paper presents DePro, a novel LLM-based debugging method that combines reference generation, stress testing, and iterative refinement specifically for competitive programming.

Findings

DePro reduces debugging attempts by up to 64%.

DePro decreases debugging time by an average of 7.6 minutes per problem.

DePro consistently produces correct solutions on tested submissions.

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.