Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique. Despite this progress, their reasoning is often constrained by their intrinsic understanding, lacking external insights. To address this, we propose Exchange-of-Thought (EoT), a novel framework that enables cross-model communication during problem-solving. Drawing inspiration from network topology, EoT integrates four unique communication paradigms: Memory, Report, Relay, and Debate. This paper delves into the communication dynamics and volume associated with each paradigm. To counterbalance the risks of incorrect reasoning chains, we implement a robust confidence evaluation mechanism within these communications. Our experiments across diverse complex reasoning tasks demonstrate that EoT significantly surpasses established baselines, underscoring the value of external insights in enhancing LLM performance. Furthermore, we show that EoT achieves these superior results in a cost-effective manner, marking a promising advancement for efficient and collaborative AI problem-solving.

翻译：大语言模型最近通过思维链技术在复杂推理任务中取得了显著进展。然而，其推理过程往往受限于自身内在理解，缺乏外部洞察。为解决这一问题，我们提出思维交流框架，一种在问题求解过程中实现跨模型通信的新型框架。受网络拓扑结构启发，思维交流集成了四种独特的通信范式：记忆、报告、中继和辩论。本文深入探讨了每种范式下的通信动态与通信量。为抵消错误推理链带来的风险，我们在这些通信中实施了稳健的置信度评估机制。在多种复杂推理任务上的实验表明，思维交流显著超越了现有基准模型，充分证明了外部洞察在增强大语言模型性能中的价值。此外，我们证明思维交流以低成本方式实现了这些优异成果，为高效协同的AI问题求解开辟了前景广阔的发展方向。