Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration

• URL: http://arxiv.org/abs/2609.12464v1
• Date: Fri, 11 Sep 2026 05:54:41 GMT
• Title: Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration
• Abstract summary: This paper introduces a Hierarchical Context-Resident Graph (HCRG) methodology to resolve limitations.<n>Our pipeline uses tree-sitter for Abstract Syntax Tree (AST) extraction, maps architectural edges into a Google Cloud Spanner Property Graph, and serializes this structure into a Gemini Context Cache.<n>Ultimately, while trading code complexity for reduced hallucinations, Graph RAG provides a substantially more viable, architecturally sound path for automated enterprise modernization.
• Score: 3.164177271211724
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: As enterprises modernize legacy monolithic systems to microservices, Large Language Models (LLMs) are heavily utilized for automated code translation. However, traditional vector-based Retrieval-Augmented Generation (Standard RAG) struggles to capture topological relationships. It fetches isolated chunks that sever inheritance chains, leading to high compilation failure rates. This paper introduces a Hierarchical Context-Resident Graph (HCRG) methodology to resolve these limitations. Our pipeline uses tree-sitter for Abstract Syntax Tree (AST) extraction, maps architectural edges into a Google Cloud Spanner Property Graph, and serializes this structure into a Gemini Context Cache for topological, parent-first code translation. We shift evaluation from naive text-overlap to a custom 7-metric Software Engineering framework. Traditional metrics like CodeBLEU (which scored 91% for both methods) effectively masked Standard RAG's structural failures behind syntactically plausible but broken code. Empirically, Graph RAG decisively mitigates dependency loss: API hallucination rates dropped from 56.4% to 16.2%, Dependency Resolution Quality improved from 34.8% to 65.9%, and Parent-Child Consistency rose from 26.7% to 45.5%. However, Graph RAG introduces specific trade-offs. The dense global context causes defensive over-engineering by the LLM, reducing Cyclomatic Complexity Consistency from 71.6% to 46.7%, and slightly degrades Docstring Preservation (67.0% to 61.0%). Ultimately, while trading code complexity for reduced hallucinations, Graph RAG provides a substantially more viable, architecturally sound path for automated enterprise codebase modernization.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL [34.35715901787783]
  We propose GRAIN, a single-agent framework optimized via reinforcement learning.<n>GRAIN models reasoning as a semantic parsing and tool-execution pipeline.<n>It outperforms multi-agent baselines by 16.45% in accuracy with approximately 24% lower latency.
  arXiv  Detail & Related papers  (2026-08-27T13:53:52Z)
• SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale [54.70985426016736]
  We present SkillDAG, which models inter-skill relationships as a typed directed graph.<n>Each search returns vector matches, typed-edge neighbors, and conflict signals, and a propose-then-commit protocol lets the agent register execution-backed edges.<n>On ALFWorld and SkillsBench with MiniMax-M2.7, SkillDAG reaches 67.1% success and 27.3% reward.
  arXiv  Detail & Related papers  (2026-06-02T02:45:21Z)
• GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization [50.009407518866965]
  Repository-level bug localization is a critical software engineering challenge.<n>GNNs offer a promising alternative due to their ability to model complex, repository-wide dependencies.<n>We introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks.
  arXiv  Detail & Related papers  (2026-02-14T23:22:15Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion [33.66085762717581]
  LLMs excel in localized code completion but struggle with repository-level tasks due to limited context windows.<n> GRACE builds a multi-level, multi-semantic code graph to capture both static and dynamic code semantics.<n>Experiments demonstrate that GRACE significantly outperforms state-of-the-art methods across all metrics.
  arXiv  Detail & Related papers  (2025-09-07T09:01:48Z)
• Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning [32.78218766121055]
  Graph retrieval-augmented generation (GraphRAG) has effectively enhanced large language models in complex reasoning.<n>We propose a vertically unified agentic paradigm, Youtu-GraphRAG, to jointly connect the entire framework as an intricate integration.
  arXiv  Detail & Related papers  (2025-08-27T13:13:20Z)
• Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation [69.45495166424642]
  We develop a robust and discriminative QA benchmark to measure temporal, causal, and character consistency understanding in narrative documents.<n>We then introduce Entity-Event RAG (E2RAG), a dual-graph framework that keeps separate entity and event subgraphs linked by a bipartite mapping.<n>Across ChronoQA, our approach outperforms state-of-the-art unstructured and KG-based RAG baselines, with notable gains on causal and character consistency queries.
  arXiv  Detail & Related papers  (2025-06-06T10:07:21Z)
• Towards Better Graph Neural Network-based Fault Localization Through Enhanced Code Representation [8.647406441990396]
  We propose a new graph representation, DepGraph, that reduces the complexity of the graph representation by 70% in nodes and edges. We evaluate DepGraph using Defects4j 2.0.0, and it outperforms Grace by locating 20% more faults in Top-1 and improving the Mean First Rank (MFR) and the Mean Average Rank (MAR) by over 50%.
  arXiv  Detail & Related papers  (2024-04-06T04:13:01Z)
• Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning [56.45977379288308]
  Masked autoencoder (MAE) learns to reconstruct masked graph edges or node features. Contrastive Learning (CL) maximizes the similarity between augmented views of the same graph. We propose graph contrastive masked autoencoder (GCMAE) framework to unify MAE and CL.
  arXiv  Detail & Related papers  (2023-10-24T05:06:06Z)
• SCGC : Self-Supervised Contrastive Graph Clustering [1.1470070927586016]
  Graph clustering discovers groups or communities within networks. Deep learning methods such as autoencoders cannot incorporate rich structural information. We propose Self-Supervised Contrastive Graph Clustering (SCGC)
  arXiv  Detail & Related papers  (2022-04-27T01:38:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.