arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2410.04485cs.SEcs.AIcs.MA
收藏

探索基于会话式测试套件的程序修复在SWE-bench上的潜力

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

Anton Cheshkov, Pavel Zadorozhny, Rodion Levichev, Evgeny Maslov, Ronaldo Franco Jaldin

AI总结:

本研究针对会话式补丁生成在SWE-Bench上的潜力未被专门评估的问题,开展实验验证基于LLaMA 3.1 70B的简单会话流水线的修复效果,达到47%的有效补丁生成率,可媲美当前最优水平。

摘要:

项目级自动程序修复可能为人类活动的诸多领域带来前所未有的机遇。自SWE-Bench挑战赛提出以来,已涌现出大量解决方案。补丁生成是程序修复的组成部分,基于测试套件的会话式补丁生成已被证明具备有效性,但其在SWE-Bench上的潜力尚未得到专门评估。本研究报告了旨在评估会话式补丁生成针对SWE-Bench问题的单独有效性的实验结果。实验表明,基于LLaMA 3.1 70B的简单会话式流水线可在47%的案例中生成有效补丁,这一表现与SWE-Bench上程序修复的当前最优水平相当。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑