从OpenAI o1与相关解读出发，这篇文章整理了对推理模型的理解，包括隐式CoT、类MCTS搜索、自举数据、Critic模型，以及推理能力与Agent能力之间的权衡。

This post sketches an evaluation plan for a CoT-based knowledge QA agent, covering hallucination control, answer relevancy, faithfulness, dataset design, and task-specific quality metrics.

This post outlines a simple view of prompt engineering for LLM CoT, arguing that concise instructions, divide-and-conquer task design, and better workflow decomposition can improve reasoning quality.