mlsanityData to 7 Oct 2026

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

arXiv 2604.03455 ↗First posted 3 Apr 2026cs.IR cs.CL cs.LGcited by 2

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

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

9 of 13 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing30 Jan
  2. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval17 Oct

Other references · 7

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  5. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  6. 2024Hybrid LLM: Cost-Efficient and Quality-Aware Query Routingcited by 354
  7. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 222

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Per-Query Gating of LLM Rerankers for Multi-Hop Retrievalcited by 0
  2. 2026FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
  2. 2026Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
  3. 2025LTRR: Learning To Rank Retrievers for LLMs
  4. 2026Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs
  5. 2025Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
  6. 2026One Size Does Not Fit All! Dynamic Retriever and Generator Selection for RAG
  7. 2026R3AG: Retriever Routing for Retrieval-Augmented Generation
  8. 2025Unsupervised Query Routing for Retrieval Augmented Generation