Newest papers

From Finding to Fixing: How Useful is Fault Localization for Agentic Program Repair?

Xinyu Shi, Zhou Yang, An Ran Chen · 2026 · arXiv

DOI: 10.48550/arXiv.2610.25826 · open-access PDF

Spanish

La localización de fallos (FL) tiene como objetivo identificar los lugares de código responsables de fallos de software y generalmente se evalúa por la exactitud con la que clasifica los lugares de fallos conocidos. Los agentes del modelo de lenguaje grande (LLM) están cambiando la reparación del programa y se utilizan cada vez más para buscar y razonar sobre los repositorios. Aunque los métodos FL recientes basados en LLM han mejorado la exactitud de la localización, su impacto en la reparación de agentes sigue siendo incierto. Para abordar esta brecha, llevamos a cabo un estudio empírico sistemático de FL en la reparación de agentes. Evaluamos seis métodos FL recientes en SWE-bench Verified y Defects4J con tres LLMs bajo una comisión

Machine translation (Meta M2M100); the English original follows.

Abstract

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 comm

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange