# Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench

arXiv: https://arxiv.org/abs/2604.03455 · HTML: https://mlsanity.com/paper/2604.03455/

## Key facts

- Cited by 2 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 9 of its 13 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 9 of 9)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval](https://mlsanity.com/paper/2410.13339/) (2024)
- [RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing](https://mlsanity.com/paper/2602.00296/) (2026)

## Built on by (most cited first, 2 of 2)

- [Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval](https://mlsanity.com/paper/2609.22880/) (2026)
- [FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents](https://mlsanity.com/paper/2609.34358/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation pipelines span a wide range of retrieval strategies that differ substantially in token cost and capability. Selecting the right strategy per query is a practical efficiency problem, yet no routing classifiers have been trained on RAGRouter-Bench citepwang2026ragrouterbench, a recently released benchmark of 7,727 queries spanning four knowledge domains, each annotated with one of three canonical query types: factual, reasoning, and summarization. We present the first systematic evaluation of lightweight classifier-based routing on this benchmark. Five classical classifiers are evaluated under three feature regimes, namely, TF-IDF, MiniLM sentence embeddings citepreimers2019sbert, and hand-crafted structural features, yielding 15 classifier feature combinations. Our best configuration, TF-IDF with an SVM, achieves a macro-averaged F1 of 0.928 and an accuracy of 93.2%, while simulating 28.1% token savings relative to always using the most expensive paradigm. Lexical TF-IDF features outperform semantic sentence embeddings by 3.1 macro-F1 points, suggesting that surface keyword patterns are strong predictors of query-type complexity. Domain-level analysis reveals that medical queries are hardest to route and legal queries most tractable. These results establish a reproducible query-side baseline and highlight the gap that corpus-aware routing must close.