Xinyu Shi, Zhou Yang, An Ran Chen · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.25826 · cited by 0 works (OpenAlex) · open-access PDF
大型语言模型(LLM)代理正在改变程序修复,并且越来越多地用于搜索和推理存储库。尽管最近的基于LLM的FL方法对软件故障负责的代码位置进行了改进,但其对代理修复轨迹的影响仍然不清楚。为了解决这个差距,我们正在对代理修复中的FL进行系统性经验评估研究。我们正在评估SWE-bench Verified和defects4J上的六种最近的FL方法,在共同修复框架下有三种LLM和分析16248修复轨迹的LLM方法。我们还研究了黄金位置和bug-cause描述,作为FL在不同的修复环境中的指导方针。我们研究的FL方法并不一致地提高修复成功,并且在使用更高的地面修复点时,测试的错误定位并不能
Machine translation (Meta M2M100); the English original follows.
Fault localization (FL) aims to identify code locations responsible for software failures and is commonly evaluated by how accurately it ranks known fault locations. Large language model (LLM) agents are changing program repair and are increasingly used to search and reason over repositories. Although recent LLM-based FL methods have improved localization accuracy, their impact on agentic repair remains unclear. To address this gap, we conduct a systematic empirical study of FL in agentic repair. We evaluate six recent FL methods on SWE-bench Verified and Defects4J with three LLMs under a common repair framework and analyze 16,248 repair trajectories. We also examine gold locations and bug-cause descriptions as forms of FL guidance across different repair contexts. The studied FL methods do not consistently improve repair success, and higher localization accuracy does not consistently lead to larger repair gains. Yet FL guides agents' early search and helps them reach relevant code sooner. Accurate locations can reduce repair token use by up to 39.2\%, but current FL methods often consume more tokens than they save during repair. Experiments with gold guidance suggest that FL has greater potential when bug inputs contain fewer location clues. Providing bug causes can further improve repair success beyond locations alone. We also find that ground truth from a single reference patch does not fully capture the locations used by successful repairs. These findings help clarify the value of FL in agentic repair and inform future work on its design and evaluation.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Code (set theory), Reliability engineering, Fault (geology), Software, Empirical research
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.25826, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange