HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
In-depth Analysis of Graph-based RAG in a Unified Framework
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptability, interpretability, and trustworthiness. A number of graph-based RAG methods have been proposed in the literature. However, these methods have not been systematically and comprehensively compared under the same experimental settings. In this paper, we first summarize a unified framework to incorporate all graph-based RAG methods from a high-level perspective. We then extensively compare representative graph-based RAG methods over a range of questing-answering (QA) datasets -- from specific questions to abstract questions -- and examine the effectiveness of all methods, providing a thorough analysis of graph-based RAG approaches. As a byproduct of our experimental analysis, we are also able to identify new variants of the graph-based RAG methods over specific QA and abstract QA tasks respectively, by combining existing techniques, which outperform the state-of-the-art methods. Finally, based on these findings, we offer promising research opportunities. We believe that a deeper understanding of the behavior of existing methods can provide new valuable insights for future research.
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 9representative citing papers
IA-RAG is a hierarchical RAG framework that represents facts as Interval Event Units organized in a Thematic Forest under Allen's Interval Algebra, with Sub-graph Time Tightening for fuzzy intervals, and reports improved results on temporal QA benchmarks.
MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphRAG methods at similar cost.
H-Mem introduces a hybrid tree-plus-graph memory mechanism that evolves short-term agent memories into long-term summaries and enables efficient retrieval, reporting state-of-the-art QA results on three benchmarks.
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
EMA attaches Markers as compact summaries to graph edges for predicate-aware guidance in filtering ANN search, delivering 1.68x-12.25x speedups over prior general filtering methods while supporting dynamic updates.
DocMaster builds hierarchical document trees and multi-view semantic indices (PC-KMeans clusters plus hyper-edges) for structure-aware filtering and RAG over complex document collections.
citing papers explorer
-
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation
HyGRAG is a hierarchical graph RAG framework that constructs LLM summaries over hybrid chunk-entity graphs, retrieves via context and relation awareness across levels, and enables dynamic updates, reporting a 9.7% average accuracy gain on multi-hop reasoning tasks.
-
IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval
IA-RAG is a hierarchical RAG framework that represents facts as Interval Event Units organized in a Thematic Forest under Allen's Interval Algebra, with Sub-graph Time Tightening for fuzzy intervals, and reports improved results on temporal QA benchmarks.
-
MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphRAG methods at similar cost.
-
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
H-Mem introduces a hybrid tree-plus-graph memory mechanism that evolves short-term agent memories into long-term summaries and enables efficient retrieval, reporting state-of-the-art QA results on three benchmarks.
-
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
-
SkillRAE: Agent Skill-Based Context Compilation for Retrieval-Augmented Execution
SkillRAE organizes skills into a graph and compiles compact, grounded contexts for LLM agents, yielding 11.7% gains on SkillsBench over prior RAE methods.
-
EvoRAG: Making Knowledge Graph-based RAG Automatically Evolve through Feedback-driven Backpropagation
EvoRAG adds a feedback-driven backpropagation step that attributes response quality to individual knowledge-graph triplets and updates the graph to raise reasoning accuracy by 7.34 percent over prior KG-RAG methods.
-
EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates
EMA attaches Markers as compact summaries to graph edges for predicate-aware guidance in filtering ANN search, delivering 1.68x-12.25x speedups over prior general filtering methods while supporting dynamic updates.
-
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
DocMaster builds hierarchical document trees and multi-view semantic indices (PC-KMeans clusters plus hyper-edges) for structure-aware filtering and RAG over complex document collections.