mlsanityData to 7 Oct 2026

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

arXiv 2403.14403 ↗First posted 21 Mar 2024cs.CL cs.AIcited by 437

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

Abstract (arXiv)

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as Question-Answering (QA). However, even though there are various approaches dealing with queries of different complexities, they either handle simple queries with unnecessary computational overhead or fail to adequately address complex multi-step queries; yet, not all user requests fall into only one of the simple or complex categories. In this work, we propose a novel adaptive QA framework, that can dynamically select the most suitable strategy for (retrieval-augmented) LLMs from the simplest to the most sophisticated ones based on the query complexity. Also, this selection process is operationalized with a classifier, which is a smaller LM trained to predict the complexity level of incoming queries with automatically collected labels, obtained from actual predicted outcomes of models and inherent inductive biases in datasets. This approach offers a balanced strategy, seamlessly adapting between the iterative and single-step retrieval-augmented LLMs, as well as the no-retrieval methods, in response to a range of query complexities. We validate our model on a set of open-domain QA datasets, covering multiple query complexities, and show that ours enhances the overall efficiency and accuracy of QA systems, compared to relevant baselines including the adaptive retrieval approaches. Code is available at: https://github.com/starsuzi/Adaptive-RAG.

Key facts. Cited by 437 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 31 of its 44 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

31 of 44 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  11. 2021Improving language models by retrieving from trillions of tokenscited by 1,278
  12. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
18 more
  1. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  3. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  5. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  6. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  8. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  9. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  10. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  11. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  12. 2022RealTime QA: What's the Answer Right Now?cited by 239
  13. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  14. 2019End-to-End Open-Domain Question Answering with BERTserinicited by 152
  15. 2020Efficient One-Pass End-to-End Entity Linking for Questionscited by 76
  16. 2020Answering Open-Domain Questions of Varying Reasoning Steps from Textcited by 43
  17. 2022Visconde: Multi-document QA with GPT-3 and Neural Rerankingcited by 23
  18. 2023Test-Time Self-Adaptive Small Language Models for Question Answeringcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 74; 2025: 153; 2026: 210.

437 papers.

Sort:

By area:

  1. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  2. 2025ZeroSearch: Incentivize the Search Capability of LLMs without Searchingcited by 203
  3. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 200
  4. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  5. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  6. 2024Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approachcited by 117
  7. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  8. 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learningcited by 68
  9. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 64
  10. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 57
  11. 2025VideoRAG: Retrieval-Augmented Generation over Video Corpuscited by 55
  12. 2025SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesiscited by 55
38 more
  1. 2025WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoningcited by 50
  2. 2025Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Surveycited by 47
  3. 2024EPIC: Efficient Position-Independent Caching for Serving Large Language Modelscited by 45
  4. 2025In-depth Analysis of Graph-based RAG in a Unified Frameworkcited by 45
  5. 2024Rationale-Guided Retrieval Augmented Generation for Medical Question Answeringcited by 41
  6. 2024SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generationcited by 40
  7. 2025GFM-RAG: Graph Foundation Model for Retrieval Augmented Generationcited by 40
  8. 2025IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theorycited by 40
  9. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  10. 2025Parametric Retrieval Augmented Generationcited by 38
  11. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Modelscited by 37
  12. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  13. 2024RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysiscited by 33
  14. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Homecited by 33
  15. 2024Teola: Towards End-to-End Optimization of LLM-based Applicationscited by 32
  16. 2025ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewardingcited by 32
  17. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learningcited by 32
  18. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learningcited by 30
  19. 2024PersonaRAG: Enhancing Retrieval-Augmented Generation Systems with User-Centric Agentscited by 28
  20. 2024TC-RAG:Turing-Complete RAG's Case study on Medical LLM Systemscited by 28
  21. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 28
  22. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  23. 2024MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexitycited by 28
  24. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generationcited by 27
  25. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  26. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  27. 2025Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicingcited by 24
  28. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfacescited by 24
  29. 2024Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Basescited by 23
  30. 2024HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applicationscited by 22
  31. 2025LongRoPE2: Near-Lossless LLM Context Window Scalingcited by 21
  32. 2024Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)cited by 20
  33. 2024KGARevion: An AI Agent for Knowledge-Intensive Biomedical QAcited by 20
  34. 2024Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspectivecited by 20
  35. 2024RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generationcited by 20
  36. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
  37. 2024ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generatorcited by 19
  38. 2024SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedbackcited by 19

50 most cited of 437 All 437 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
  2. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
  3. 2024Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
  4. 2026Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
  5. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  6. 2025Retrieval Augmented Question Answering: When Should LLMs Admit Ignorance?
  7. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering
  8. 2025Multiple Abstraction Level Retrieve Augment Generation