mlsanityData to 7 Oct 2026

RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems

arXiv 2511.12979 ↗First posted 17 Nov 2025cs.LG cs.DBcited by 2

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 13 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

9 of 13 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions26 May

Other references · 8

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2023Qwen Technical Reportcited by 3,273
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2023SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verificationcited by 359
  5. 2024Llumnix: Dynamic Scheduling for Large Language Model Servingcited by 167
  6. 2024RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generationcited by 97
  7. 2024BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systemscited by 84
  8. 2024TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textcited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026PRISM: Fast Online LLM Serving via Scheduling-Memory Co-designcited by 1
  2. 2026Evaluating the accuracy of KV cache reuse techniquescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving
  2. 2026RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
  3. 2024RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation
  4. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  5. 2024Toward Optimal Search and Retrieval for RAG
  6. 2024Long Context RAG Performance of Large Language Models
  7. 2025RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
  8. 2024Towards Understanding Systems Trade-offs in Retrieval-Augmented Generation Model Inference