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
La localisation de défauts potentiels d'agent unique (FL) vise à identifier les emplacements de code responsables des défauts logiciels et est généralement évaluée par la précision de la localisation des emplacements de défauts connus. Les agents du grand modèle de langue (LLM) modifient la réparation du programme et sont de plus en plus utilisés pour rechercher et raisonner sur les dépôts. Bien que les méthodes FL récentes basées sur LLM aient amélioré la précision de la localisation sous un cadre commun de réparation et analysent les trajectoires de réparation de l'agent reste incertaine. Pour résoudre cette lacune, nous réalisons une étude empirique systématique de FL dans la réparation de l'agent. Nous évaluons six méthodes FL
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