Salvato in:
Dettagli Bibliografici
Autori principali: Bevziuk, Kostiantyn, Fatula, Andrii, Opanasenko, Svetozar Lashin Yaroslav, Tukhtarova, Anna, Sharma, Ashok Jallepalli Pradeepkumar, Shrivastava, Hritvik
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.08876
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911201763524608
author Bevziuk, Kostiantyn
Fatula, Andrii
Opanasenko, Svetozar Lashin Yaroslav
Tukhtarova, Anna
Sharma, Ashok Jallepalli Pradeepkumar
Shrivastava, Hritvik
author_facet Bevziuk, Kostiantyn
Fatula, Andrii
Opanasenko, Svetozar Lashin Yaroslav
Tukhtarova, Anna
Sharma, Ashok Jallepalli Pradeepkumar
Shrivastava, Hritvik
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08876
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
Bevziuk, Kostiantyn
Fatula, Andrii
Opanasenko, Svetozar Lashin Yaroslav
Tukhtarova, Anna
Sharma, Ashok Jallepalli Pradeepkumar
Shrivastava, Hritvik
Software Engineering
Artificial Intelligence
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.
title Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2510.08876