Latent tokens are gaining attention for enhancing reasoning in large language models (LLMs), yet their internal mechanisms remain unclear. This paper examines the problem from a reliability perspective, uncovering fundamental weaknesses: latent tokens function as uninterpretable placeholders rather than encoding faithful reasoning. While resistant to perturbation, they promote shortcut usage over genuine reasoning. We focus on Chain-of-Continuous-Thought (COCONUT), which claims better efficiency and stability than explicit Chain-of-Thought (CoT) while maintaining performance. We investigate this through two complementary approaches. First, steering experiments perturb specific token subsets, namely COCONUT and explicit CoT. Unlike CoT tokens, COCONUT tokens show minimal sensitivity to steering and lack reasoning-critical information. Second, shortcut experiments evaluate models under biased and out-of-distribution settings. Results on MMLU and HotpotQA demonstrate that COCONUT consistently exploits dataset artifacts, inflating benchmark performance without true reasoning. These findings reposition COCONUT as a pseudo-reasoning mechanism: it generates plausible traces that conceal shortcut dependence rather than faithfully representing reasoning processes.

翻译：潜藏令牌在增强大型语言模型推理能力方面日益受到关注，但其内部机制仍不明确。本文从可靠性角度审视该问题，揭示了其根本缺陷：潜藏令牌仅作为不可解释的占位符运行，而非编码可信的推理过程。虽然对扰动具有抵抗性，但它们会促进捷径使用而非真正的推理。我们聚焦于连续思维链模型，该模型声称在保持性能的同时，比显式思维链具有更高的效率和稳定性。我们通过两种互补方法对此进行研究。首先，通过导向实验扰动特定令牌子集（即COCONUT与显式CoT）。与CoT令牌不同，COCONUT令牌对导向表现出极低的敏感性，且缺乏推理关键信息。其次，捷径实验在偏置和分布外设置下评估模型。在MMLU和HotpotQA上的结果表明，COCONUT持续利用数据集伪影，在不进行真实推理的情况下虚增基准性能。这些发现将COCONUT重新定位为伪推理机制：它生成看似合理的追踪轨迹以掩盖对捷径的依赖，而非真实反映推理过程。