# BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

arXiv: https://arxiv.org/abs/2607.26497 · HTML: https://mlsanity.com/paper/2607.26497/

## Key facts

- Cited by 1 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 23 of its 28 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 23 of 23)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models](https://mlsanity.com/paper/2405.14831/) (2024)
- [From RAG to Memory: Non-Parametric Continual Learning for Large Language Models](https://mlsanity.com/paper/2502.14802/) (2025)
- [GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning](https://mlsanity.com/paper/2405.20139/) (2024)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations](https://mlsanity.com/paper/2102.10073/) (2021)
- [LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora](https://mlsanity.com/paper/2510.10114/) (2025)
- [EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge](https://mlsanity.com/paper/2605.05253/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory](https://mlsanity.com/paper/2608.12888/) (2026)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) spans lexical and dense retrieval, graph-based indexing, and agentic search, but these paradigms are usually evaluated on different benchmarks at one corpus size, leaving their accuracy-cost scaling unclear. To bridge this gap, we present a controlled study that varies corpus size along 28 strictly nested tiers spanning roughly 450-fold, while holding questions and a fixed bedrock of relevant and adversarial documents unchanged. Under one reader model and one judging protocol, we measure official accuracy, construction and query tokens, and latency. The results reveal a scale-dependent crossover rather than an unconditional winner. File-System Agent leads at the smallest shared tiers, but its sequential exploration costs 39 times more query tokens at the bedrock and becomes less effective as the search space grows. Around 10 million corpus tokens, BM25 overtakes it and leads at every larger shared tier, with a margin approaching 20 points at full scale. BM25 also anchors the low-cost end of the Pareto frontier without LLM-based construction. Dense retrieval remains efficient but less accurate, whereas graph-based RAG encounters construction walls before deployment scale and its scalable variants remain below BM25 at shared tiers. Overall, corpus growth increasingly favors global candidate ranking: lexical retrieval is the strongest scalable default, while agentic reasoning works best after ranked discovery rather than in place of it.