The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Abstract
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
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“BoT overcomes the limitations of single-query methods (e.g., manual exemplar reliance) and multi-query approaches (e.g., computational inefficiency) by introducing a meta-buffer that distills”
From A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024) · cites this paper as Yang et al., 2024
In the citing paper
“Notably, BoT enhances smaller models, with Llama3-8B + BoT surpassing Llama3-70B in accuracy, showing its potential to democratize efficient reasoning at scale.”
From A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024) · cites this paper as Yang et al., 2024
In the citing paper
“Experiments across 10 benchmarks demonstrate its state-of-the-art performance, achieving gains of 11% on Game of 24, 20% on Geometric Shapes, and 51% on Checkmate-in-One, while using just 12% of the computational cost of multi-query methods like Treeof-Thoughts.”
From A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024) · cites this paper as Yang et al., 2024
In the citing paper
“To address this, Yang et al. [2024] introduced Buffer of Thoughts (BoT), a framework that enhances LLMs through reusable high-level reasoning patterns.”
From A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024) · cites this paper as Yang et al., 2024
In the citing paper
“BoT retrieves task-specific thought-templates (e.g., structured problem-solving approaches) and adaptively instantiates them, mimicking human analogical reasoning to eliminate manual prompt design and recursive exploration.”
From A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications (2024) · cites this paper as Yang et al., 2024
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Large Language Models are Zero-Shot Reasoners
Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022) · arXiv · doi:10.48550/arxiv.2205.11916 · Cited by 2,013
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876
Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.10403 · Cited by 834
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Besta, M., Blach, N., Kubicek, A., Gerstenberger, R., Podstawski, M., Gianinazzi, L., Gajda, J., Lehmann, T., Niewiadomski, H., Nyczyk, P., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.09687 · Cited by 556
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
Zhou, D., Schärli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., Le, Q., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.10625 · Cited by 380
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
Self-citationAugmented Language Models: a Survey
Mialon, G., Dessì, R., Lomeli, M., Nalmpantis, C., Pasunuru, R., Raileanu, R., Rozière, B., Schick, T., Dwivedi-Yu, J., Celikyilmaz, A., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.07842 · Cited by 160
Chen, W., Ma, X., Wang, X., & Cohen, W. W. (2022) · arXiv · doi:10.48550/arxiv.2211.12588 · Cited by 125
Cited by
AFlow: Automating Agentic Workflow Generation
Zhang, J., Xiang, J., Yu, Z., Teng, F., Chen, X., Chen, J., Zhuge, M., Cheng, X., Hong, S., Wang, J., et al. (2024) · arXiv · doi:10.48550/arxiv.2410.10762 · Cited by 359
Self-citationA Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
Sahoo, P., Singh, A. K., Saha, S., Jain, V., Mondal, S., & Chadha, A. (2024) · arXiv · doi:10.48550/arxiv.2402.07927 · Cited by 288
Zhao, S., Yang, Y., Wang, Z., He, Z., Qiu, L. K., & Qiu, L. (2024) · arXiv · doi:10.48550/arxiv.2409.14924 · Cited by 180
Yager, K. G. (2024) · Digital Discovery · doi:10.1039/d4dd00178h · Cited by 12
Fang, J., Peng, Y., Zhang, X., Wang, Y., Yi, X., Zhang, G., Xu, Y., Wu, B., Liu, S., Li, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.07407 · Cited by 6
Large Language Model Reasoning Failures
Song, P., Han, P., & Goodman, N. (2026) · arXiv · doi:10.48550/arxiv.2602.06176 · Cited by 3
Memory in the Age of AI Agents
Hu, Y., Liu, S., Yue, Y., Zhang, G., Liu, B., Zhu, F., Lin, J., Guo, H., Dou, S., Xi, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2512.13564 · Cited by 389
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052 · Cited by 70
Self-citationScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
Wang, Y., Yang, L., Li, G., Wang, M., & Aragam, B. (2025) · arXiv · doi:10.48550/arxiv.2502.04306
Self-citationPeng, C., Jiang, M., Zhou, Y., & Wu, L. (2026) · Proceedings of the ACM on Software Engineering · doi:10.1145/3808141
Metadata
- Authors
- Yang, L., Yu, Z., Zhang, T., Cao, S., Xu, M., Zhang, W., Gonzalez, J., & Cui, B.
- Venue
- Advances in Neural Information Processing Systems 37
- Published
- 2024
- Pages
- 113519-113544
- Cited by
- 17
- References
- 10
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.