Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval

📅 2025-10-09
📈 Citations: 0
Influential: 0
📄 PDF

career value

166K/year
🤖 AI Summary
To address the low efficiency of code understanding and file localization in large-scale software repositories, this paper proposes a graph-augmented hybrid retrieval framework. First, it leverages large language models (LLMs) to extract semantic summaries and generate fine-grained vector embeddings, while integrating static analysis to construct a knowledge graph encoding syntactic–semantic relationships—including inheritance, method calls, and references. Second, it introduces a graph-aware retrieval expansion mechanism that jointly optimizes semantic similarity matching and subgraph traversal, supporting LLM-generated constrained natural language queries and interpretable reasoning. Experimental results demonstrate significant improvements in accuracy and robustness for problem-driven file retrieval across multiple open-source projects. The approach achieves a substantial leap in automated code understanding capability and establishes a scalable, knowledge-infused infrastructure for intelligent development toolchains.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Converting software repositories into vectorized knowledge graphs
Capturing semantic relationships for automated repository development
Combining semantic retrieval with graph-aware expansion techniques
Innovation

Methods, ideas, or system contributions that make the work stand out.

Vectorized knowledge graph for repository decomposition
Hybrid retrieval combining semantic and graph expansion
LLM-based assistant for constrained graph requests
🔎 Similar Papers
2024-06-03arXiv.orgCitations: 23