Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

BM25 Beats Dense and Agentic RAG at Scale, New Study Finds

AI By Crimson AI Hugging Face Papers 31 July 2026 · 00:00 31 views
Share: X Telegram

A controlled scaling study of retrieval-augmented generation (RAG) reveals a scale-dependent crossover: while agentic search leads at small corpora, BM25 overtakes it around 10 million tokens and dominates at larger scales, becoming the strongest scalable default.

BM25 Beats Dense and Agentic RAG at Scale, New Study Finds

Key points

Retrieval-augmented generation (RAG) has become a cornerstone of modern AI systems, but choosing the right retrieval paradigm—lexical, dense, graph-based, or agentic—remains a challenge. A new study from Hugging Face researchers provides a systematic comparison across corpus sizes, revealing that the best approach depends heavily on scale.

The study, titled "BM25 Wins at Scale," evaluates four RAG paradigms across 28 nested corpus tiers spanning a 450-fold range, using a single reader model and judging protocol. The researchers measured accuracy, token usage, and latency while keeping questions and a fixed set of relevant and adversarial documents unchanged.

Results show a clear crossover: the File-System Agent, an agentic approach, leads at the smallest corpus sizes but becomes inefficient as the search space grows, consuming 39 times more query tokens at the largest scale. Around 10 million corpus tokens, BM25—a classical lexical retrieval method—overtakes the agent and maintains its lead at every larger tier, with an accuracy margin approaching 20 points at full scale.

Dense retrieval remains efficient but less accurate, while graph-based RAG faces construction bottlenecks before reaching deployment scale. The study concludes that corpus growth favors global candidate ranking, making lexical retrieval the strongest scalable default, while agentic reasoning is best applied after ranked discovery rather than as a replacement for it.

ParadigmPerformance at Small ScalePerformance at Full ScaleQuery Token Cost (Full Scale)
File-System AgentLeadsOvertaken by BM2539x baseline
BM25LowerLeads by ~20 pointsLow (no LLM construction)
Dense RetrievalEfficientLess accurateLow
Graph-based RAGN/AConstruction wallsN/A
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1