Repository-level software repair faces challenges in bridging semantic gaps between issue descriptions and code patches. Existing approaches, which mostly depend on large language models (LLMs), suffer from semantic ambiguities, limited structural context understanding, and insufficient reasoning capability. To address these limitations, we propose KGCompass with two innovations: (1) a novel repository-aware knowledge graph (KG) that accurately links repository artifacts (issues and pull requests) and codebase entities (files, classes, and functions), allowing us to effectively narrow down the vast search space to only 20 most relevant functions with accurate candidate bug locations and contextual information, and (2) a path-guided repair mechanism that leverages KG-mined entity path, tracing through which allows us to augment LLMs with relevant contextual information to generate precise patches along with their explanations. Experimental results in the SWE-Bench-Lite demonstrate that KGCompass achieves state-of-the-art repair performance (45.67%) and function-level localization accuracy (51.33%) across open-source approaches, costing only $0.20 per repair. Our analysis reveals that among successfully localized bugs, 69.7% require multi-hop traversals through the knowledge graph, without which LLM-based approaches struggle to accurately locate bugs. The knowledge graph built in KGCompass is language agnostic and can be incrementally updated, making it a practical solution for real-world development environments.

翻译：暂无翻译