customaize-agent:thought-based-reasoning

Chain-of-Thought (CoT) prompting and its variants encourage LLMs to generate intermediate reasoning steps before arriving at a final answer, significantly improving performance on complex reasoning tasks. These techniques transform how models approach problems by making implicit reasoning explicit.

| Technique | When to Use | Complexity | Accuracy Gain |

| Zero-shot CoT | Quick reasoning, no examples available | Low | +20-60% | | Few-shot CoT | Have good examples, consistent format needed | Medium | +30-70% | | Self-Consistency | High-stakes decisions, need confidence | Medium | +10-20% over CoT | | Tree of Thoughts | Complex problems requiring exploration | High | +50-70% on hard tasks |

在處理需要逐步邏輯、多步驟算術、常識推理、符號操作的複雜推理任務或簡單提示失敗的問題時使用 - 透過模板、決策矩陣和研究支援的模式提供思想鍊和相關提示技術（零樣本 CoT、自我一致性、思想樹、最少到最多、ReAct、PAL、反射）的全面指南 來源：neolabhq/context-engineering-kit。