mlsanityData to 14 Oct 2026

HedraRAG: Coordinating LLM Generation and Database Retrieval in Heterogeneous RAG Serving

arXiv 2507.09138 ↗First posted 12 Jul 2025cs.DB cs.LGcited by 3

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

Abstract (arXiv)

This paper addresses emerging system-level challenges in heterogeneous retrieval-augmented generation (RAG) serving, where complex multi-stage workflows and diverse request patterns complicate efficient execution. We present HedraRAG, a runtime system built on a graph-based abstraction that exposes optimization opportunities across stage-level parallelism, intra-request similarity, and inter-request skewness. These opportunities are realized through dynamic graph transformations, such as node splitting, reordering, edge addition, and dependency rewiring, applied to wavefronts of subgraphs spanning concurrent requests. The resulting execution plans are mapped onto hybrid CPU-GPU pipelines to improve resource utilization and reduce latency. Evaluations across a wide range of RAG workflows demonstrate speedups exceeding 1.5x and reaching up to 5x over existing frameworks, showcasing the effectiveness of coordinated generation and retrieval in serving environments.

Key facts. Cited by 3 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 32 of its 63 references that are in the map. First posted on arXiv 12 Jul 2025.

Builds on

32 of 63 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving18 Mar
  2. 2025TeleRAG: Efficient Retrieval-Augmented Generation Inference with Lookahead Retrieval28 Feb
  3. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research22 May
  4. 2024PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design8 Mar
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  6. 2023Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models15 Oct

Other references · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2024The Llama 3 Herd of Modelscited by 14,715
  6. 2020Scaling Laws for Neural Language Modelscited by 6,586
  7. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  9. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  10. 2017Billion-scale similarity search with GPUscited by 2,497
  11. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  12. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
14 more
  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  2. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  3. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  4. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  6. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  7. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  8. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  9. 2023LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compressioncited by 453
  10. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 372
  11. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 223
  12. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  13. 2024OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMscited by 72
  14. 2025Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuningcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025FastTTS: Accelerating Test-Time Scaling for Edge LLM Reasoningcited by 3
  2. 2025DS SERVE: A Framework for Efficient and Scalable Neural Retrievalcited by 2
  3. 2026Natural Language Query to Configuration for Retrieval Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RAGe: A Retrieval-Augmented Generation Evaluation Framework
  2. 2026OpRAG: A Resource-Deterministic Runtime for GPU-Backed Multi-Stage RAG Workflows
  3. 2026RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems
  4. 2025Harmonia: End-to-End RAG Serving Optimization
  5. 2026RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems
  6. 2025RAGDoll: Efficient Offloading-based Online RAG System on a Single GPU
  7. 2025VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG
  8. 2026AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines