English

Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench

Software Engineering 2024-10-08 v1 Artificial Intelligence Multiagent Systems

Abstract

Automatic program repair at project level may open yet to be seen opportunities in various fields of human activity. Since the SWE-Bench challenge was presented, we have seen numerous of solutions. Patch generation is a part of program repair, and test suite-based conversational patch generation has proven its effectiveness. However, the potential of conversational patch generation has not yet specifically estimated on SWE-Bench. This study reports experimental results aimed at evaluating the individual effectiveness of conversational patch generation on problems from SWE-Bench. The experiments show that a simple conversational pipeline based on LLaMA 3.1 70B can generate valid patches in 47\% of cases, which is comparable to the state-of-the-art in program repair on SWE-Bench.

Cite

@article{arxiv.2410.04485,
  title  = {Exploring the Potential of Conversational Test Suite Based Program Repair on SWE-bench},
  author = {Anton Cheshkov and Pavel Zadorozhny and Rodion Levichev and Evgeny Maslov and Ronaldo Franco Jaldin},
  journal= {arXiv preprint arXiv:2410.04485},
  year   = {2024}
}

Comments

3 pages, 2 figures, 1 algorithm, appendix

R2 v1 2026-06-28T19:10:18.099Z