思维缓冲区：基于大语言模型的思维增强推理
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
AI总结：
本文提出思维增强推理方法BoT，通过元缓冲区存储跨任务提炼的思维模板并动态实例化，结合缓冲区管理器提升大模型推理准确性与鲁棒性，在10项任务上超越SOTA且成本极低。
摘要：
我们提出了思维缓冲区（Buffer of Thoughts, BoT），一种新颖且通用的思维增强推理方法，旨在提升大语言模型（LLMs）的准确性、效率和鲁棒性。具体而言，我们提出了元缓冲区（meta-buffer），用于存储一系列信息丰富的高层次思维，即思维模板（thought-template），这些模板是从各种任务的问题解决过程中提炼出来的。随后，针对每个问题，我们检索相关的思维模板，并利用特定的推理结构自适应地实例化它，以进行高效推理。为了保证可扩展性和稳定性，我们进一步提出了缓冲区管理器（buffer-manager），以动态更新元缓冲区，从而随着更多任务的解决增强元缓冲区的能力。我们在10个具有挑战性的推理密集型任务上进行了广泛实验，并相较于先前的SOTA方法取得了显著的性能提升：在Game of 24上提升11%，在Geometric Shapes上提升20%，在Checkmate-in-One上提升51%。进一步分析表明，我们的BoT具有卓越的泛化能力和模型鲁棒性，同时平均仅需多查询提示方法（如tree/graph of thoughts）12%的成本。值得注意的是，我们发现Llama3-8B+BoT有潜力超越Llama3-70B模型。我们的项目可在以下网址获取：https://github.com/YangLing0818/buffer-of-thoughts-llm
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
