| From Local to Global: A Graph RAG Approach to Query-Focused Summarization |
2024 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5, Q6, Q8, Q9 |
GraphRAG-Microsoft, # GraphRAG 2025–2026:代表论文、研究脉络与问题演进 |
| HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models |
2024 |
P0 |
pdf-level |
Q1, Q3, Q5, Q6, Q7 |
HippoRAG |
| GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation |
2025 |
P0 |
pdf-level |
Q1, Q2, Q3, Q6, Q7 |
GraphRAG-Bench |
| LightRAG: Simple and Fast Retrieval-Augmented Generation |
2025 |
P0 |
pdf-level |
Q1, Q2, Q3, Q6, Q8 |
LightRAG |
| BubbleRAG - Evidence-Driven RAG for Black-Box KGs |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q5, Q6 |
BubbleRAG - Evidence-Driven RAG for Black-Box KGs |
| Ex-GraphRAG - Interpretable Evidence Routing for Graph-Augmented LLMs |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
Ex-GraphRAG - Interpretable Evidence Routing for Graph-Augmented LLMs |
| Graph-R1 - Agentic GraphRAG via End-to-end Reinforcement Learning |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
Graph-R1 - Agentic GraphRAG via End-to-end Reinforcement Learning |
| GraphRAG on Consumer Hardware - Local LLMs for Healthcare EHR Schema Retrieval |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
GraphRAG on Consumer Hardware - Local LLMs for Healthcare EHR Schema Retrieval |
| GraphRAG-R1 - Process-Constrained Reinforcement Learning for GraphRAG |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
GraphRAG-R1 - Process-Constrained Reinforcement Learning for GraphRAG |
| GraphSteal - Structural Knowledge Stealing from GraphRAG |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
GraphSteal - Structural Knowledge Stealing from GraphRAG |
| LLM-Wiki - Retrieval as Reasoning via Self-Evolving Agent-Native Retrieval |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
LLM-Wiki - Retrieval as Reasoning via Self-Evolving Agent-Native Retrieval |
| MOSAIC: Query-Aware Exploration Policy Adaptation for GraphRAG |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
MOSAIC |
| PersonalAI 2.0 - Planning Graph Traversal for Personalized LLM Agents |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
PersonalAI 2.0 - Planning Graph Traversal for Personalized LLM Agents |
| Rethinking Agentic RAG - LLM-Driven Logical Retrieval Beyond Embeddings |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
Rethinking Agentic RAG - LLM-Driven Logical Retrieval Beyond Embeddings |
| TechGraphRAG - Agentic Graph-Augmented RAG Framework |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
TechGraphRAG - Agentic Graph-Augmented RAG Framework |
| WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora |
2026 |
P0 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
WildGraphBench |
| Biomedical Knowledge Graph-Optimized Prompt Generation for Large Language Models |
— |
P1 |
abstract-level |
Q1, Q2, Q3, Q6, Q8 |
KG-RAG |
| CFT-RAG: An Entity Tree Based Retrieval Augmented Generation Algorithm With Cuckoo Filter |
— |
P1 |
abstract-level |
Q1, Q2, Q3, Q4, Q8 |
CFT-RAG |
| GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models |
— |
P1 |
abstract-level |
Q1, Q3, Q7, Q8, Q9 |
GRIL |
| Generative Dense Retrieval: Memory Can Be a Burden |
— |
P1 |
abstract-level |
Q1, Q3, Q5, Q6, Q8 |
Generative-Dense-Retrieval-Memory-Burden |
| Generative Retrieval Overcomes Limitations of Dense Retrieval but Struggles with Identifier Ambiguity |
— |
P1 |
abstract-level |
Q1, Q3, Q6, Q9 |
Generative-Retrieval-Identifier-Ambiguity |
| Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation |
— |
P1 |
abstract-level |
Q1, Q2, Q3, Q6, Q7 |
Medical-Graph-RAG |
| RECON: Multimodal GraphRAG for Visually Rich Documents with Intra-Page Reflection and Inter-Page Connection |
— |
P1 |
abstract-level |
Q1, Q2, Q3, Q6, Q8 |
RECON |
| RIGHT ANSWER AT THE RIGHT TIME: Temporal Retrieval-Augmented Generation via Graph Summarization |
— |
P1 |
abstract-level |
Q1, Q2, Q3, Q7, Q8 |
STAR-RAG |
| 关于嵌入式检索的理论局限性 |
— |
P1 |
abstract-level |
Q1, Q3, Q6, Q7, Q8 |
嵌入式检索的理论局限性 |
| G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering |
2024 |
P1 |
pdf-level |
Q1, Q3, Q7, Q8, Q9 |
G-Retriever |
| E2GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness |
2025 |
P1 |
pdf-level |
Q1, Q2, Q3, Q5, Q7 |
E²GraphRAG |
| LINEAR RAG: Linear Graph Retrieval Augmented Generation on Large-Scale Corpora |
2025 |
P1 |
pdf-level |
Q1, Q2, Q3, Q5, Q7 |
LinearRAG |
| MMGraphRAG - Interpretable Multimodal Knowledge Graphs |
2025 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
MMGraphRAG - Interpretable Multimodal Knowledge Graphs |
| A2RAG - Adaptive Agentic Graph Retrieval |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
A2RAG - Adaptive Agentic Graph Retrieval |
| CacheRAG - Semantic Caching for KGQA |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
CacheRAG - Semantic Caching for KGQA |
| ChatP&ID - GraphRAG for Engineering Diagrams |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
ChatP&ID - GraphRAG for Engineering Diagrams |
| Do We Still Need GraphRAG - Agentic Search Benchmark |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
Do We Still Need GraphRAG - Agentic Search Benchmark |
| Enhancing Automated Short Answer Grading with GraphRAG |
2026 |
P1 |
abstract-level |
Q1, Q3, Q7, Q8, Q9 |
GraphRAG-Automated-Grading |
| GraphRAG-Router - Cost-Efficient Routing over GraphRAGs and LLMs |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
GraphRAG-Router - Cost-Efficient Routing over GraphRAGs and LLMs |
| Lightfoot: Graph Retrieval-Augmented Generation with Exact, Model-Free Document Deletion |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q6, Q8 |
Lightfoot |
| LogicPoison - Logical Attacks on GraphRAG |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
LogicPoison - Logical Attacks on GraphRAG |
| MemGraphRAG - Memory-based Multi-Agent GraphRAG |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
MemGraphRAG - Memory-based Multi-Agent GraphRAG |
| NaviRAG - Active Knowledge Navigation for RAG |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
NaviRAG - Active Knowledge Navigation for RAG |
| Reasoning Bottleneck in Graph-RAG - Structured Prompting and Context Compression |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
Reasoning Bottleneck in Graph-RAG - Structured Prompting and Context Compression |
| Reliable Graph-RAG for Codebases - AST vs LLM Knowledge Graphs |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q7 |
Reliable Graph-RAG for Codebases - AST vs LLM Knowledge Graphs |
| SEM-RAG - Structure-Preserving Multimodal Graph Compilation |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q6 |
SEM-RAG - Structure-Preserving Multimodal Graph Compilation |
| STAR - Semantic-Tuned and Tail-Adaptive Retriever for GraphRAG |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q4, Q5 |
STAR - Semantic-Tuned and Tail-Adaptive Retriever for GraphRAG |
| TCAR-Gen - Temporal Graph Retrieval with Evidence Fusion |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q5, Q6 |
TCAR-Gen - Temporal Graph Retrieval with Evidence Fusion |
| TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning |
2026 |
P1 |
pdf-level |
Q1, Q2, Q3, Q6, Q8 |
TopoGraphRAG-Bench |
| StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization |
2024 |
P2 |
pdf-level |
Q1, Q2, Q7, Q8, Q9 |
StructRAG |