思想的一切：打破彭罗斯三角形的法则，用于思维生成

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

最近對於大型語言模型（LLMs）的進展已經通過將複雜問題分解為更易處理的語言序列，即所謂的「思維」，徹底改變了決策過程。一個有效的思維設計應該考慮三個關鍵觀點：性能、效率和靈活性。然而，現有的思維最多只能展現這三個屬性中的兩個。為了解決這些限制，我們引入了一種新穎的思維提示方法，稱為「一切思維」（XoT），以打破現有思維範式的「彭羅斯三角定律」。XoT利用預訓練的強化學習和蒙特卡羅樹搜索（MCTS）將外部領域知識納入思維中，從而增強LLMs的能力，使其能夠高效地泛化到未見問題。通過MCTS-LLM協作思維修訂框架的應用，這種方法能夠自主地生成高質量的全面認知映射，並最大程度地減少LLM的交互作用。此外，XoT賦予LLMs參與無限制思考的能力，從而為具有多個解決方案的問題提供靈活的認知映射。

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.