Mathematical reasoning remains a significant challenge for large language models (LLMs), despite progress in prompting techniques such as Chain-of-Thought (CoT). We present **Chain of Mathematically Annotated Thought (CoMAT)**, which enhances reasoning through two stages: *Symbolic Conversion* (converting natural language queries into symbolic form) and *Reasoning Execution* (deriving answers from symbolic representations). CoMAT operates entirely with a single LLM and without external solvers. Across four LLMs, CoMAT outperforms traditional CoT on six out of seven benchmarks, achieving gains of 4.48% on MMLU-Redux (MATH) and 4.58% on GaoKao MCQ. In addition to improved performance, CoMAT ensures faithfulness and verifiability, offering a transparent reasoning process for complex mathematical tasks

翻译：尽管思维链（CoT）等提示技术取得了进展，但数学推理对于大语言模型（LLMs）而言仍然是一项重大挑战。我们提出了**数学标注思维链（CoMAT）**，该方法通过两个阶段增强推理能力：*符号转换*（将自然语言查询转换为符号形式）和*推理执行*（从符号表示推导答案）。CoMAT完全在单一LLM内运行，无需外部求解器。在四个LLM上的实验表明，CoMAT在七个基准测试中的六项上超越了传统CoT方法，在MMLU-Redux（MATH）上实现了4.48%的性能提升，在GaoKao MCQ上提升了4.58%。除了性能改进外，CoMAT确保了推理过程的忠实性与可验证性，为复杂数学任务提供了透明的推理路径。