mlsanityData to 7 Oct 2026

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

arXiv 2501.06713 ↗First posted 12 Jan 2025cs.AIcited by 28

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

The growing demand for efficient and lightweight Retrieval-Augmented Generation (RAG) systems has highlighted significant challenges when deploying Small Language Models (SLMs) in existing RAG frameworks. Current approaches face severe performance degradation due to SLMs' limited semantic understanding and text processing capabilities, creating barriers for widespread adoption in resource-constrained scenarios. To address these fundamental limitations, we present MiniRAG, a novel RAG system designed for extreme simplicity and efficiency. MiniRAG introduces two key technical innovations: (1) a semantic-aware heterogeneous graph indexing mechanism that combines text chunks and named entities in a unified structure, reducing reliance on complex semantic understanding, and (2) a lightweight topology-enhanced retrieval approach that leverages graph structures for efficient knowledge discovery without requiring advanced language capabilities. Our extensive experiments demonstrate that MiniRAG achieves comparable performance to LLM-based methods even when using SLMs while requiring only 25% of the storage space. Additionally, we contribute a comprehensive benchmark dataset for evaluating lightweight RAG systems under realistic on-device scenarios with complex queries. We fully open-source our implementation and datasets at: https://github.com/HKUDS/MiniRAG.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 22 references that are in the map. First posted on arXiv 12 Jan 2025.

Builds on

18 of 22 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation28 Oct
  2. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 16

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  3. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  5. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  6. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  7. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 694
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  9. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  10. 2024MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Casescited by 216
  11. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  12. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 144
4 more
  1. 2024A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthinesscited by 125
  2. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  3. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 118
  4. 2024ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systemscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 15; 2026: 13.

28 papers.

Sort:

By area:

  1. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agentscited by 49
  2. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  3. 2025AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understandingcited by 14
  4. 2025Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrievalcited by 10
  5. 2025Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinkingcited by 6
  6. 2025Understanding DeepResearch via Reportscited by 6
  7. 2025Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimizationcited by 5
  8. 2025HKRAG: Holistic Knowledge Retrieval-Augmented Generation Over Visually-Rich Documentscited by 5
  9. 2025A Survey of LLM × DATAcited by 4
  10. 2025GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generationcited by 3
  11. 2026When Small Models Are Right for Wrong Reasons: Process Verification for Trustworthy Agentscited by 3
  12. 2026PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligencecited by 3
16 more
  1. 2026Agents-K1: Towards Agent-native Knowledge Orchestrationcited by 3
  2. 2026RAGExplorer: A Visual Analytics System for the Comparative Diagnosis of RAG Systemscited by 2
  3. 2025TERAG: Token-Efficient Graph-Based Retrieval-Augmented Generationcited by 1
  4. 2025Query-Centric Graph Retrieval Augmented Generationcited by 1
  5. 2026HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generationcited by 1
  6. 2025ELITE: Embedding-Less retrieval with Iterative Text Explorationcited by 0
  7. 2025DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systemscited by 0
  8. 2026ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulationscited by 0
  9. 2025Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QAcited by 0
  10. 2026MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inferencecited by 0
  11. 2026GroupRAG: Cognitively Inspired Group-Aware Retrieval and Reasoning via Knowledge-Driven Problem Structuringcited by 0
  12. 2026Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?cited by 0
  13. 2026UniD3: A Knowledge Graph-Enhanced RAG Framework for Drug-Disease Discovery and Reasoningcited by 0
  14. 2026ConRAG: Lightweight inference of multi-hop relationscited by 0
  15. 2026ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World Consultationscited by 0
  16. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Graph Retrieval-Augmented Generation: A Survey
  2. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation
  4. 2025mmRAG: A Modular Benchmark for Retrieval-Augmented Generation over Text, Tables, and Knowledge Graphs
  5. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
  6. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  7. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights
  8. 2025LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora