mlsanityData to 7 Oct 2026

Think-then-Act: A Dual-Angle Evaluated Retrieval-Augmented Generation

arXiv 2406.13050 ↗First posted 18 Jun 2024cs.CLcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 1 more
Abstract (arXiv)

Despite their impressive capabilities, large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. Enhancing LLMs with retrieval mechanisms to fetch relevant information from external sources offers a promising solution. Inspired by the proverb "Think twice before you act," we propose a dual-angle evaluated retrieval-augmented generation framework textitThink-then-Act. Unlike previous approaches that indiscriminately rewrite queries or perform retrieval regardless of necessity, or generate temporary responses before deciding on additional retrieval, which increases model generation costs, our framework employs a two-phase process: (i) assessing the input query for clarity and completeness to determine if rewriting is necessary; and (ii) evaluating the model's capability to answer the query and deciding if additional retrieval is needed. Experimental results on five datasets show that the textitThink-then-Act framework significantly improves performance. Our framework demonstrates notable improvements in accuracy and efficiency compared to existing baselines and performs well in both English and non-English contexts. Ablation studies validate the optimal model confidence threshold, highlighting the resource optimization benefits of our approach.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 30 of its 44 references that are in the map. First posted on arXiv 18 Jun 2024.

Builds on

30 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2023Graph-ToolFormer: To Empower LLMs with Graph Reasoning Ability via Prompt Augmented by ChatGPT10 Apr
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 27

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  11. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  12. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
15 more
  1. 2023Active Retrieval Augmented Generationcited by 506
  2. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 364
  3. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  4. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  5. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 250
  6. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  7. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  8. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  9. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  10. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 61
  11. 2023Query Expansion by Prompting Large Language Modelscited by 56
  12. 2022Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformercited by 45
  13. 2023Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Modelscited by 42
  14. 2023WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpuscited by 29
  15. 2021You Only Need One Model for Open-domain Question Answeringcited by 17

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  2. 2025CCSK:Cognitive Convection of Self-Knowledge Based Retrieval Augmentation for Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
  2. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  3. 2024E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation
  4. 2026To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval
  5. 2025Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers
  6. 2026Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models
  7. 2025Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
  8. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation