用向量图结构理解代码库，提升问题驱动的文件检索效率。
Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
- 将代码库转为包含语义与架构信息的向量知识图谱。
- 结合语义检索与图结构扩展，显著提升文件定位准确率。
- 适合开发人员快速理解复杂项目结构，辅助自动化维护。
我们提出一个仓库分解系统，将大型软件仓库转换为反映项目架构与语义结构的向量知识图谱，捕捉语义关系，实现后续开发的高度自动化。该图谱编码了包含、实现、引用、调用和继承等语法关系，并为节点补充大语言模型生成的摘要与向量嵌入。采用混合检索管道，结合语义检索与图感知扩展；由大语言模型驱动的助手可生成受约束的只读图查询，并输出面向人类的解释。
原文摘要 · Abstract (English)
We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant level of automatization of further repository development. The graph encodes syntactic relations such as containment, implementation, references, calls, and inheritance, and augments nodes with LLM-derived summaries and vector embeddings. A hybrid retrieval pipeline combines semantic retrieval with graph-aware expansion, and an LLM-based assistant formulates constrained, read-only graph requests and produces human-oriented explanations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。