一切关于思维的事物：违抗彭罗斯三角定律以生成思维

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation

November 7, 2023

作者: Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei Zhang, Si Qin, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

cs.AI

摘要

最近大型语言模型（LLMs）的进展彻底改变了决策过程，通过将复杂问题分解为更易处理的语言序列，这些序列被称为“思维”。一个有效的思维设计应考虑三个关键视角：性能、效率和灵活性。然而，现有的思维最多只能展现这些属性中的两个。为了解决这些局限性，我们引入了一种名为“一切思维”（XoT）的新颖思维引导方法，以打破现有思维范式的“彭罗斯三角律”。XoT利用预训练的强化学习和蒙特卡洛树搜索（MCTS）将外部领域知识融入思维中，从而增强LLMs的能力，使其能够高效地推广到未知问题。通过利用MCTS-LLM协作思维修订框架，这种方法能够自主地生成高质量的全面认知映射，减少LLM的交互。此外，XoT赋予LLMs参与无限制思考的能力，为具有多种解决方案的问题提供灵活的认知映射。

English

Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as ``thoughts''. An effective thought design should consider three key perspectives: performance, efficiency, and flexibility. However, existing thought can at most exhibit two of these attributes. To address these limitations, we introduce a novel thought prompting approach called ``Everything of Thoughts'' (XoT) to defy the law of ``Penrose triangle of existing thought paradigms. XoT leverages pretrained reinforcement learning and Monte Carlo Tree Search (MCTS) to incorporate external domain knowledge into thoughts, thereby enhancing LLMs' capabilities and enabling them to generalize to unseen problems efficiently. Through the utilization of the MCTS-LLM collaborative thought revision framework, this approach autonomously produces high-quality comprehensive cognitive mappings with minimal LLM interactions. Additionally, XoT empowers LLMs to engage in unconstrained thinking, allowing for flexible cognitive mappings for problems with multiple solutions.