Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits <swi> to enter latent mode and </swi> to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) <swi> is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.

翻译：潜在思维链通过用连续的隐藏状态循环替代可见推理轨迹来压缩推理过程，但现有公式难以使用标准在线强化学习（RL）进行优化，且因果解释性差。我们的核心发现是，单对显式边界标记可同时解决这两个问题：离散的进入和退出锚点使潜在块兼容标准在线RL，同时这些锚点为机制分析提供了天然切入点。基于此，我们提出可切换潜在推理框架SWITCH。模型生成<swi>进入潜在模式，生成</swi>退出模式。由于边界为普通离散标记，GRPO策略比率在每个决策点均有明确定义。同一锚点还使潜在步骤可直接进行探测和因果干预。我们采用可见到潜在的课程学习及Switch-GRPO目标训练模型，该目标通过循环潜在计算传播梯度。SWITCH在相似规模下持续优于先前基于隐藏状态循环的潜在推理方法。通过边界标记的机制分析进一步揭示三个发现：（i）<swi>是高度局部化的学习型切换策略而非风格化伪影；（ii）其开启的潜在步骤执行问题特定的因果关键计算，而非作为惰性占位符；（iii）该计算集中在单次隐藏状态转换入口处。这些结果共同表明：隐藏状态循环型潜在推理既可通过RL训练，又可直接进行机制分析——包括分析在线RL如何从内部改进模型本身。