Skip to main content
PaperAI Agentsv1.0

From Local to Global: A Graph RAG Approach to Query-Focused Summarization

by Microsoft Research · open-source · Last verified 2026-03-17

Presents GraphRAG, which uses LLM-generated knowledge graphs and community detection to enable query-focused summarization over entire text corpora. Unlike standard RAG which answers local questions from text chunks, GraphRAG enables global sensemaking queries by reasoning over interconnected entity communities at multiple granularities.

https://arxiv.org/abs/2404.16130
B+
B+Good
Adoption: AQuality: AFreshness: B+Citations: AEngagement: F

Specifications

License
MIT
Pricing
open-source
Capabilities
knowledge-graph, global-summarization, community-detection, query-focused-summarization
Integrations
Use Cases
corpus-sensemaking, global-qa, knowledge-graph-construction, research
API Available
No
Tags
rag, knowledge-graph, graph, summarization, community-detection
Added
2026-03-17
Completeness
100%

Index Score

70.9
Adoption
82
Quality
88
Freshness
76
Citations
82
Engagement
0

Put AI to work for your business

Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.

Explore the full AI ecosystem on Agents as a Service