mlsanityData to 7 Oct 2026

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

arXiv 2403.05313 ↗First posted 8 Mar 2024cs.CL cs.AIcited by 75

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

also in 1 more
Abstract (arXiv)

We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks; on average of relatively increasing rating scores by 13.63% on code generation, 16.96% on mathematical reasoning, 19.2% on creative writing, and 42.78% on embodied task planning. The demo page can be found at https://craftjarvis.github.io/RAT

Key facts. Cited by 75 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 50 of its 61 references that are in the map. First posted on arXiv 8 Mar 2024.

Builds on

50 of 61 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Survey18 Dec
  2. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec
  3. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner18 May

Other references · 47

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  8. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  9. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  10. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  11. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  12. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
35 more
  1. 2021Program Synthesis with Large Language Modelscited by 3,509
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  3. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  6. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  7. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  8. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 895
  10. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  11. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 871
  12. 2022PAL: Program-aided Language Modelscited by 635
  13. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  14. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  15. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoningcited by 331
  16. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  17. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  18. 2023Continual Pre-training of Language Modelscited by 194
  19. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Modelscited by 170
  20. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
  21. 2022Faithful Reasoning Using Large Language Modelscited by 130
  22. 2022Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answeringcited by 126
  23. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  24. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 120
  25. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 117
  26. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 97
  27. 2023STEVE-1: A Generative Model for Text-to-Behavior in Minecraftcited by 95
  28. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  29. 2023Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Predictioncited by 39
  30. 2022Continual Training of Language Models for Few-Shot Learningcited by 33
  31. 2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 33
  32. 2024Selecting Large Language Model to Fine-tune via Rectified Scaling Lawcited by 33
  33. 2023Retrieval-Generation Synergy Augmented Large Language Modelscited by 26
  34. 2023Adapting a Language Model While Preserving its General Knowledgecited by 23
  35. 2023GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidencecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 25; 2025: 31; 2026: 19.

75 papers.

Sort:

By area:

  1. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  2. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  3. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 100
  4. 2024Speculative RAG: Enhancing Retrieval Augmented Generation through Draftingcited by 76
  5. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  6. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 58
  7. 2024Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMscited by 48
  8. 2024Rationale-Guided Retrieval Augmented Generation for Medical Question Answeringcited by 41
  9. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  10. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  11. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 39
  12. 2024Self-Reflection in LLM Agents: Effects on Problem-Solving Performancecited by 38
38 more
  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  2. 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agentscited by 30
  3. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  4. 2024Knowledge Editing through Chain-of-Thoughtcited by 26
  5. 2025A Survey of Multimodal Hallucination Evaluation and Detectioncited by 26
  6. 2025Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agentscited by 23
  7. 2024ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Promptingcited by 20
  8. 2024ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generatorcited by 19
  9. 2024Refiner: Restructure Retrieval Content Efficiently to Advance Question-Answering Capabilitiescited by 16
  10. 2025CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answeringcited by 15
  11. 2024Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Modelscited by 12
  12. 2024OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Modelscited by 12
  13. 2025Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughtscited by 12
  14. 2024Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generationcited by 11
  15. 2025Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoningcited by 11
  16. 2024Mars: Situated Inductive Reasoning in an Open-World Environmentcited by 10
  17. 2024LLMs are not Zero-Shot Reasoners for Biomedical Information Extractioncited by 9
  18. 2025OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraftcited by 9
  19. 2024DeepNote: Note-Centric Deep Retrieval-Augmented Generationcited by 8
  20. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
  21. 2025Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notescited by 7
  22. 2026Procedural Knowledge at Scale Improves Reasoningcited by 7
  23. 2025RAG-Adapter: A Plug-and-Play RAG-enhanced Framework for Long Video Understandingcited by 6
  24. 2025MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfercited by 6
  25. 2025Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysiscited by 5
  26. 2025Am I on the Right Track? What Can Predicted Query Performance Tell Us about the Search Behaviour of Agentic RAGcited by 5
  27. 2025Cache Mechanism for Agent RAG Systemscited by 5
  28. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answeringcited by 4
  29. 2026Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overheadcited by 4
  30. 2025RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoningcited by 3
  31. 2025Injecting External Knowledge into the Reasoning Process Enhances Retrieval-Augmented Generationcited by 3
  32. 2025Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answeringcited by 3
  33. 2026Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAGcited by 3
  34. 2024Self-Explained Keywords Empower Large Language Models for Code Generationcited by 2
  35. 2025K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressorcited by 2
  36. 2025Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflectioncited by 2
  37. 2026Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documentscited by 2
  38. 2026RAG over Thinking Traces Can Improve Reasoning Taskscited by 2

50 most cited of 75 All 75 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
  2. 2026Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study
  3. 2026When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
  4. 2026RecaLLM: Addressing the Lost-in-Thought Phenomenon with Explicit In-Context Retrieval
  5. 2025Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
  6. 2025LAG: Logic-Augmented Generation from a Cartesian Perspective
  7. 2026Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used
  8. 2025Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding