潜在的思维链作为规划：将推理与言说解耦
Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization
AI总结：
PLaT通过解耦推理与言说，实现了更灵活的推理过程和更高的可扩展性。
摘要：
链式思维（CoT）使大语言模型（LLMs）能够解决复杂问题，但受限于在离散标记空间中进行推理的计算成本和推理路径崩溃。最近的潜在推理方法尝试通过在连续隐藏状态中进行推理来优化效率。然而，这些方法通常作为从显式推理步骤到潜在状态的黑箱端到端映射操作，并且通常在推理时需要预定义数量的潜在步骤。在本文中，我们引入PLaT（带有潜在思维的规划），一种将潜在推理重新表述为规划的框架，通过从根本上将推理与言说解耦。我们将推理建模为潜在规划状态的确定性轨迹，而一个独立的解码器在需要时将这些想法转化为文本。这种解耦使模型能够动态决定何时终止推理，而不是依赖于固定的超参数。在数学基准上的实验证明了一种明显的权衡：尽管PLaT的贪心准确率低于基线，但其在推理多样性方面表现出更好的可扩展性。这表明PLaT学习了一个稳健、更广泛的问题空间，为推理时间搜索提供了一个透明且可扩展的基础。我们的代码可在https://github.com/yunsaijc/PLaT中找到。
英文摘要：
Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and early token commitments in discrete reasoning traces. Recent latent reasoning approaches attempt to optimize efficiency by performing reasoning within continuous hidden states. However, many such methods optimize latent states end to end without a trained interface for intermediate textual readout, and several representative configurations use a pre-defined number of latent steps during inference. In this work, we introduce \textbf{PLaT} (\textbf{P}lanning with \textbf{La}tent \textbf{T}houghts), a framework that decouples latent planning from verbalization. The Planner deterministically evolves latent planning states, while an independent Decoder provides textual readouts when needed. Answer-aware textual stopping allows the latent rollout to use a problem-dependent number of groups rather than a pre-specified chain length. PLaT achieves competitive coverage at larger $k$ in several mathematical settings, with lower Pass@1: on Llama-1B GSM8K, it reaches 80.59\% Pass@128 versus CODI's 72.37\%. These results support PLaT as a candidate-generation interface supplying multiple textual readouts for downstream verification or reranking.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
