mlsanityData to 7 Oct 2026

How You Ask Matters! Adaptive RAG Robustness to Query Variations

arXiv 2604.10745 ↗First posted 12 Apr 2026cs.CLcited by 3

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent, and their impact on Adaptive RAG remains under-explored. We introduce the first large-scale benchmark of diverse yet semantically identical query variations, combining human-written and model-generated rewrites. Our benchmark facilitates a systematic evaluation of Adaptive RAG robustness by examining its key components across three dimensions: answer quality, computational cost, and retrieval decisions. We discover a critical robustness gap, where small surface-level changes in queries dramatically alter retrieval behavior and accuracy. Although larger models show better performance, robustness does not improve accordingly. These findings reveal that Adaptive RAG methods are highly vulnerable to query variations that preserve identical semantics, exposing a critical robustness challenge.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 50 references that are in the map. First posted on arXiv 12 Apr 2026.

Builds on

27 of 50 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level9 Jul
  2. 2025RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems1 Jun
  3. 2025Out of Style: RAG's Fragility to Linguistic Variation11 Apr
  4. 2025QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors5 Apr
  5. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home22 Jan
  6. 2024Retrieval Augmented Generation for Domain-specific Question Answering23 Apr
  7. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  5. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  7. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  8. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  9. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  10. 2022Large Language Models with Controllable Working Memorycited by 169
  11. 2021Evaluating the Robustness of Retrieval Pipelines with Query Variation Generatorscited by 33
  12. 2024Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMscited by 27
7 more
  1. 2024DMQR-RAG: Diverse Multi-Query Rewriting for RAGcited by 26
  2. 2025Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicingcited by 24
  3. 2022Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellingscited by 23
  4. 2019GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errorscited by 22
  5. 2022CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typoscited by 22
  6. 2025LLM-Independent Adaptive RAG: Let the Question Speak for Itselfcited by 7
  7. 2018Boosting Search Performance Using Query Variationscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuitscited by 0
  2. 2026CompCQR: Compositional Query Generation for Training-Free Conversational Searchcited by 0
  3. 2026Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responsescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented Generation
  2. 2025Evaluating the Retrieval Robustness of Large Language Models
  3. 2025Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control
  4. 2024RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
  5. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  6. 2026CQC-RAG: Robust Retrieval-Augmented Generation via Cross-Query Consistency
  7. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  8. 2026Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation