mlsanityData to 14 Oct 2026

Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval

arXiv 2601.03908 ↗First posted 7 Jan 2026cs.CLcited by 3

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing noise and limiting performance gains. In this work, we propose Decide Then Retrieve (DTR), a training-free framework that adaptively determines when retrieval is necessary and how external information should be selected. DTR leverages generation uncertainty to guide retrieval triggering and introduces a dual-path retrieval mechanism with adaptive information selection to better handle sparse and ambiguous queries. Extensive experiments across five open-domain QA benchmarks, multiple model scales, and different retrievers demonstrate that DTR consistently improves EM and F1 over standard RAG and strong retrieval-enhanced baselines, while reducing unnecessary retrievals. The code and data used in this paper are available at https://github.com/ChenWangHKU/DTR.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 28 of its 42 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

28 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis24 May
  2. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation31 Mar
  3. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity21 Mar
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  7. 2024Qwen2 Technical Reportcited by 2,120
  8. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  9. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  10. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  11. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  12. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 433
12 more
  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  2. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 249
  3. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  4. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certaintycited by 187
  5. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  6. 2023How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrievalcited by 118
  7. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  8. 2020BERT-QE: Contextualized Query Expansion for Document Re-rankingcited by 40
  9. 2022Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbationcited by 10
  10. 2024Database-Augmented Query Representation for Information Retrievalcited by 5
  11. 2025ImpRAG: Retrieval-Augmented Generation with Implicit Queriescited by 5
  12. 2025PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAGcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Position: Modular Memory is the Key to Continual Learning Agentscited by 8
  2. 2026TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Modelscited by 1
  3. 2026Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
  2. 2025Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
  3. 2024CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
  4. 2025To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation
  5. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  6. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
  7. 2026Interpretable Uncertainty for Adaptive Retrieval and Reasoning in Question Answering
  8. 2026Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval