mlsanityData to 14 Oct 2026

CaGR-RAG: Context-aware Query Grouping for Disk-based Vector Search in RAG Systems

arXiv 2505.01164 ↗First posted 2 May 2025cs.DCcited by 1

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

Abstract (arXiv)

Modern embedding models capture both semantic and syntactic structures of queries, often mapping different queries to similar regions in vector space. This results in non-uniform cluster access patterns in disk-based vector search systems, particularly in Retrieval Augmented Generation (RAG) framework. While existing approaches optimize individual queries, they overlook the impact of cluster access patterns, failing to account for the locality effects of queries that access similar clusters. This oversight reduces cache efficiency and increases search latency due to excessive disk I/O. To address this, we introduce CaGR-RAG, a context-aware query grouping mechanism that organizes queries based on shared cluster access patterns. Additionally, it incorporates opportunistic cluster prefetching to minimize cache misses during transitions between query groups, further optimizing retrieval performance. Experimental results show that CaGR-RAG reduces 99th percentile tail latency by up to 51.55% while consistently maintaining a higher cache hit ratio than the baseline.

Key facts. Cited by 1 paper 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 12 of its 19 references that are in the map. First posted on arXiv 2 May 2025.

Builds on

12 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024EdgeRAG: Online-Indexed RAG for Edge Devices30 Dec
  2. 2024Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference16 Dec

Other references · 10

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  4. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  5. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  7. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  8. 2021SPANN: Highly-efficient Billion-scale Approximate Nearest Neighbor Searchcited by 35
  9. 2022Manu: A Cloud Native Vector Database Management Systemcited by 18
  10. 2024Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segmentcited by 17

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cloud-Native Vector Search: A Comprehensive Performance Analysiscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systems
  2. 2026QVCache: A Query-Aware Vector Cache
  3. 2025Leveraging Approximate Caching for Faster Retrieval-Augmented Generation
  4. 2025Cosmos: A CXL-Based Full In-Memory System for Approximate Nearest Neighbor Search
  5. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving
  6. 2025Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications
  7. 2026RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems
  8. 2025SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases