mlsanityData to 14 Oct 2026

EdgeRAG: Online-Indexed RAG for Edge Devices

arXiv 2412.21023 ↗First posted 30 Dec 2024cs.LGcited by 13

On the map: Retrieval-augmented generation → RAG pipeline design and evaluation

Abstract (arXiv)

Deploying Retrieval Augmented Generation (RAG) on resource-constrained edge devices is challenging due to limited memory and processing power. In this work, we propose EdgeRAG which addresses the memory constraint by pruning embeddings within clusters and generating embeddings on-demand during retrieval. To avoid the latency of generating embeddings for large tail clusters, EdgeRAG pre-computes and stores embeddings for these clusters, while adaptively caching remaining embeddings to minimize redundant computations and further optimize latency. The result from BEIR suite shows that EdgeRAG offers significant latency reduction over the baseline IVF index, but with similar generation quality while allowing all of our evaluated datasets to fit into the memory.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 5 of its 30 references that are in the map. First posted on arXiv 30 Dec 2024.

Builds on

5 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems16 Nov

Other references · 4

  1. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  2. 2023Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruningcited by 415
  3. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Textcited by 220
  4. 2022Retrieval Augmented Visual Question Answering with Outside Knowledgecited by 94

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 3.

13 papers.

Sort:

By area:

  1. 2025MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAGcited by 11
  2. 2025Accelerating Mobile Language Model via Speculative Decoding and NPU-Coordinated Executioncited by 5
  3. 2025LEANN: A Low-Storage Vector Indexcited by 4
  4. 2026Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agentscited by 2
  5. 2025LEKA:LLM-Enhanced Knowledge Augmentationcited by 1
  6. 2025CaGR-RAG: Context-aware Query Grouping for Disk-based Vector Search in RAG Systemscited by 1
  7. 2025WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browserscited by 1
  8. 2025PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devicescited by 1
  9. 2025DGRAG: Distributed Graph-based Retrieval-Augmented Generation in Edge-Cloud Systemscited by 0
  10. 2025CoSense-LLM: Semantics at the Edge with Cost- and Uncertainty-Aware Cloud-Edge Cooperationcited by 0
  11. 2025CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computingcited by 0
  12. 2026From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAGcited by 0
1 more
  1. 2026RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving
  2. 2026Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite
  3. 2024Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architectures
  4. 2025FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation
  5. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)
  6. 2025DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation
  7. 2025Online-Optimized RAG for Tool Use and Function Calling
  8. 2026RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems