Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focusing on local token-level attribution, such that the high-level semantic roles of reasoning steps and their transitions remain underexplored. In this paper, we introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics. Specifically, to capture the evolving semantics of CoT reasoning, each reasoning step is represented via spectral analysis of token-level embeddings and clustered into semantically coherent latent states. To characterize the global structure of reasoning, we model their progression as a Markov chain, yielding a structured and interpretable view of the reasoning process. This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.

翻译：近年来，思维链（CoT）提示技术的进展使得大语言模型（LLM）能够执行多步推理。然而，此类推理的可解释性仍然有限，先前的研究主要集中于局部词元级别的归因分析，导致推理步骤的高层语义角色及其转换过程尚未得到充分探索。本文提出了一种状态感知转换框架，将CoT轨迹抽象为结构化的潜在动态。具体而言，为捕捉CoT推理中不断演化的语义，我们通过对词元级别嵌入进行谱分析来表示每个推理步骤，并将其聚类为语义连贯的潜在状态。为刻画推理的全局结构，我们将其演进过程建模为马尔可夫链，从而获得推理过程的结构化且可解释的视图。该抽象框架支持多种分析，包括语义角色识别、时序模式可视化以及一致性评估。