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

arXiv: https://arxiv.org/abs/2510.08876 · HTML: https://mlsanity.com/paper/2510.08876/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 4 of 4)

- [Atlas: Few-shot Learning with Retrieval Augmented Language Models](https://mlsanity.com/paper/2208.03299/) (2022)
- [CodeGemma: Open Code Models Based on Gemma](https://mlsanity.com/paper/2406.11409/) (2024)
- [AST-T5: Structure-Aware Pretraining for Code Generation and Understanding](https://mlsanity.com/paper/2401.03003/) (2024)
- [GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding](https://mlsanity.com/paper/2409.04183/) (2024)

## Built on by (most cited first, 1 of 1)

- [DeepDiscovery: A Location-Inference Framework for Task-Level Repository Understanding](https://mlsanity.com/paper/2606.22906/) (2026)

## Abstract (arXiv)

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.