Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought reasoning operates directly in the continuous latent space, enabling computation beyond discrete linguistic representations. While both approaches exploit iterative computation, their comparative capabilities remain underexplored. In this work, we present a formal analysis showing that latent thought admits more efficient parallel computation than inherently sequential CoT. In contrast, CoT enables approximate counting and sampling through stochastic decoding. These separations suggest the tasks for which depth-driven recursion is more suitable, thereby offering practical guidance for choosing between reasoning paradigms.

翻译：链式思维（CoT）通过显式生成中间标记来激发大型语言模型中的推理过程。相比之下，潜在思维推理直接在连续潜在空间中操作，实现了超越离散语言表征的计算能力。尽管两种方法均利用迭代计算，但它们的比较性能力仍未得到充分探索。本研究通过形式化分析表明，潜在思维允许比固有顺序的链式思维更高效的并行计算。相反，链式思维通过随机解码实现了近似计数与采样。这些差异揭示了深度驱动递归更适用的任务类型，从而为推理范式的选择提供了实践指导。