Recent advancements in large-scale models, such as GPT-4, have showcased remarkable capabilities in addressing standard queries. However, when facing complex problems that require multi-step logical reasoning, their accuracy dramatically decreases. Current research has explored the realm of \textit{prompting engineering} to bolster the inferential capacities of these models. Our paper unveils a pioneering prompting technique, dubbed \textit{Graph of Thoughts (GoT)}. Through testing on a trio of escalating challenges: the 24-point game, resolution of high-degree polynomial equations, and derivation of formulas for recursive sequences, our method outperformed GPT-4, achieving accuracy improvements of $89.7\%$, $86\%$, and $56\%$ for each respective task. Moreover, when juxtaposed with the state-of-the-art (SOTA) prompting method, \textit{Tree of Thought (ToT)}, our approach registered an average accuracy boost of $23\%$, $24\%$, and $15\%$.

翻译：近期以GPT-4为代表的大规模模型在处理常规查询时展现出卓越能力，但在面对需要多步逻辑推理的复杂问题时，其准确率急剧下降。当前研究已开始探索"提示工程"领域以增强这些模型的推理能力。本文提出一种名为"思维图"(Graph of Thoughts, GoT)的开创性提示技术。通过在三个难度递增的挑战（24点游戏、高次多项式方程求解、递推数列公式推导）中进行测试，该方法在各项任务中分别超越GPT-4，准确率提升达89.7%、86%和56%。与当前最先进(SOTA)的提示方法"思维树"(Tree of Thought, ToT)相比，本方法在准确率上平均提升23%、24%和15%。