mlsanityData to 14 Oct 2026

ScalableRAG: High-Quality RAG at Zero Ingestion Cost

arXiv 2607.25135 ↗First posted 27 Jul 2026cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in RAG aim to optimize for performance by paying high ingestion costs for knowledge ingestion: building knowledge graphs or extracting SQL tables. In this work we show that the operations that such knowledge bases allow can be replicated with zero ingestion costs (not even a vector database); in fact our solution, Zero-Ingestion ScalableRAG, handily out-performs all baselines (including knowledge graph approaches) in three out of the six corpora considered here, and only marginally missing maximum performance on the other three, with average accuracy across all six datasets 7.36% above the next most competitive baseline. It achieves this by keeping a workspace of document sets and values sets that it can write into and read from, allowing for on-the-fly aggregative reasoning in all situations where grouping is required on a primary key that is in one to one correspondence with a subset of the total document set. Capping the number of LLM calls by a constant independent of the corpus size, we also introduce Limited-Ingestion ScalableRAG, which does use a minimal vector database as well as an automated pattern discovery from a sample of documents, to further improve accuracy at scale. Our code is available at https://github.com/cohesity/ScalableRAG .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 87 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

16 of 87 references.

References · 16

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  7. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  8. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  9. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  10. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  11. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 270
  12. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
4 more
  1. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfacescited by 24
  2. 2023Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuningcited by 18
  3. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrievalcited by 6
  4. 2025Structured RAG for Answering Aggregative Questionscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
  2. 2025KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs
  3. 2026HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
  4. 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
  5. 2025RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
  6. 2024TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
  7. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  8. 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs