mlsanityData to 14 Oct 2026

Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

arXiv 2406.04271 ↗First posted 6 Jun 2024cs.CLcited by 91

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs). Specifically, we propose meta-buffer to store a series of informative high-level thoughts, namely thought-template, distilled from the problem-solving processes across various tasks. Then for each problem, we retrieve a relevant thought-template and adaptively instantiate it with specific reasoning structures to conduct efficient reasoning. To guarantee the scalability and stability, we further propose buffer-manager to dynamically update the meta-buffer, thus enhancing the capacity of meta-buffer as more tasks are solved. We conduct extensive experiments on 10 challenging reasoning-intensive tasks, and achieve significant performance improvements over previous SOTA methods: 11% on Game of 24, 20% on Geometric Shapes and 51% on Checkmate-in-One. Further analysis demonstrate the superior generalization ability and model robustness of our BoT, while requiring only 12% of the cost of multi-query prompting methods (e.g., tree/graph of thoughts) on average. Notably, we find that our Llama3-8B+BoT has the potential to surpass Llama3-70B model. Our project is available at: https://github.com/YangLing0818/buffer-of-thought-llm

Key facts. Cited by 91 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 48 of its 61 references that are in the map. First posted on arXiv 6 Jun 2024.

Builds on

48 of 61 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models9 Oct
  2. 2023Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models6 Oct
  3. 2023Large Language Models as Analogical Reasoners3 Oct
  4. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Models18 Aug
  5. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks22 Nov
  6. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them17 Oct
  7. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  8. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  9. 2022Large Language Models are Zero-Shot Reasoners24 May
  10. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  11. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  12. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 36

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2022Emergent Abilities of Large Language Modelscited by 2,512
  9. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  10. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  11. 2024Mixtral of Expertscited by 1,823
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
24 more
  1. 2023PaLM 2 Technical Reportcited by 1,162
  2. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  3. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,031
  4. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  6. 2022PAL: Program-aided Language Modelscited by 652
  7. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  8. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 530
  9. 2023Augmented Language Models: a Surveycited by 403
  10. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  11. 2022Emergent Analogical Reasoning in Large Language Modelscited by 240
  12. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  13. 2022Ask Me Anything: A simple strategy for prompting language modelscited by 155
  14. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 142
  15. 2022Retrieval-Augmented Multimodal Language Modelingcited by 125
  16. 2024Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffoldingcited by 117
  17. 2024Self-Discover: Large Language Models Self-Compose Reasoning Structurescited by 110
  18. 2022Language Models Can Teach Themselves to Program Bettercited by 78
  19. 2022Retrieval-based Controllable Molecule Generationcited by 44
  20. 2022E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoningcited by 28
  21. 2022Analogy Generation by Prompting Large Language Models: A Case Study of InstructGPTcited by 27
  22. 2021Programming Puzzlescited by 25
  23. 2022Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processescited by 22
  24. 2022Multimodal Analogical Reasoning over Knowledge Graphscited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 14; 2025: 34; 2026: 43.

91 papers.

Sort:

By area:

  1. 2024AFlow: Automating Agentic Workflow Generationcited by 432
  2. 2025From System 1 to System 2: A Survey of Reasoning Large Language Modelscited by 320
  3. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  4. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 143
  5. 2024Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoningcited by 110
  6. 2025Agentic Large Language Models, a surveycited by 108
  7. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 90
  8. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 66
  9. 2025ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templatescited by 63
  10. 2025Autellix: An Efficient Serving Engine for LLM Agents as General Programscited by 58
  11. 2024Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTScited by 54
  12. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
38 more
  1. 2025ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoningcited by 41
  2. 2025EXP-Bench: Can AI Conduct AI Research Experiments?cited by 37
  3. 2025Demystifying Reinforcement Learning in Agentic Reasoningcited by 33
  4. 2024Meta Reasoning for Large Language Modelscited by 29
  5. 2026Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineeringcited by 28
  6. 2025AStar: Boosting Multimodal Reasoning with Automated Structured Thinkingcited by 25
  7. 2025ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memorycited by 24
  8. 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verificationcited by 22
  9. 2024Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitationcited by 19
  10. 2025HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generationcited by 18
  11. 2026A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applicationscited by 18
  12. 2025Thought-Augmented Planning for LLM-Powered Interactive Recommender Agentcited by 17
  13. 2025Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?cited by 15
  14. 2024BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Searchcited by 13
  15. 2024Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphscited by 12
  16. 2024Typhoon 2: A Family of Open Text and Multimodal Thai Large Language Modelscited by 12
  17. 2025RARE: Retrieval-Augmented Reasoning Modelingcited by 11
  18. 2025Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instructioncited by 10
  19. 2025FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Datacited by 10
  20. 2025Policy Guided Tree Search for Enhanced LLM Reasoningcited by 9
  21. 2025ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoningcited by 9
  22. 2026MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolutioncited by 9
  23. 2026Tool Verification for Test-Time Reinforcement Learningcited by 9
  24. 2026Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnessescited by 9
  25. 2024In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Modelscited by 8
  26. 2024Stepwise Reasoning Error Disruption Attack of LLMscited by 8
  27. 2025Escaping the Verifier: Learning to Reason via Demonstrationscited by 7
  28. 2026MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillationcited by 7
  29. 2025Knowledge Augmented Complex Problem Solving with Large Language Models: A Surveycited by 6
  30. 2025Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learningcited by 6
  31. 2026The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?cited by 6
  32. 2026AdaMEM: Test-Time Adaptive Memory for Language Agentscited by 6
  33. 2025LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMscited by 5
  34. 2025Log-Augmented Generation: Scaling Test-Time Reasoning with Reusable Computationcited by 4
  35. 2026Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalabilitycited by 4
  36. 2026Thinking with Reasoning Skills: Fewer Tokens, More Accuracycited by 4
  37. 2024Towards a Science Exocortexcited by 3
  38. 2025Fast Thinking for Large Language Modelscited by 3

50 most cited of 91 All 91 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  2. 2023Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought
  3. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
  4. 2026Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs
  5. 2023Chain-of-Thought Hub: A Continuous Effort to Measure Large Language Models' Reasoning Performance
  6. 2024Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
  7. 2025Thought calibration: Efficient and confident test-time scaling
  8. 2024Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer