Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913036477923328 |
|---|---|
| author | Chakraborty, Koushik Guha, Koyel |
| author_facet | Chakraborty, Koushik Guha, Koyel |
| contents | This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling as a robust solution for navigating superseding logic and multi-hop references. Our benchmark evaluation using the Code of Federal Regulations (CFR) demonstrates that this Knowledge Graph-enhanced approach achieves a 70% accuracy improvement over standard vector-based RAG systems, providing exhaustive and precise answers for complex regulatory queries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14220 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents Chakraborty, Koushik Guha, Koyel Information Retrieval Artificial Intelligence This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling as a robust solution for navigating superseding logic and multi-hop references. Our benchmark evaluation using the Code of Federal Regulations (CFR) demonstrates that this Knowledge Graph-enhanced approach achieves a 70% accuracy improvement over standard vector-based RAG systems, providing exhaustive and precise answers for complex regulatory queries. |
| title | Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14220 |