Recent advances in large language models (LLMs) have leveraged explicit Chain-of-Thought (CoT) prompting to improve reasoning accuracy. However, most existing methods primarily compress verbose reasoning outputs. These Long-to-Short transformations aim to improve efficiency, but still rely on explicit reasoning during inference. In this work, we introduce \textbf{3TF} (\textbf{T}hought-\textbf{T}raining and \textbf{T}hought-\textbf{F}ree inference), a framework for efficient reasoning that takes a Short-to-Long perspective. We first train a hybrid model that can operate in both reasoning and non-reasoning modes, and then further train it on CoT-annotated data to internalize structured reasoning, while enforcing concise, thought-free outputs at inference time using the no-reasoning mode. Unlike compression-based approaches, 3TF improves the reasoning quality of non-reasoning outputs, enabling models to perform rich internal reasoning implicitly while keeping external outputs short. Empirically, 3TF-trained models obtain large improvements on reasoning benchmarks under thought-free inference, demonstrating that high quality reasoning can be learned and executed implicitly without explicit step-by-step generation.

翻译：近年来，大型语言模型（LLMs）通过显式的思维链（CoT）提示技术显著提升了推理准确性。然而，现有方法大多侧重于压缩冗长的推理输出。这种“长到短”的转换旨在提高效率，但在推理过程中仍依赖显式推理。本文提出一种高效推理框架——3TF（思维训练与无思维推理），采用“短到长”的视角。我们首先训练一个可在推理模式与非推理模式下运行的混合模型，随后基于CoT标注数据进一步训练，使其内化结构化推理能力，同时在推理时通过非推理模式强制生成简洁的无思维输出。与基于压缩的方法不同，3TF提升了非推理输出的推理质量，使模型能够在保持外部输出简洁的同时，隐式执行丰富的内部推理。实验表明，经3TF训练的模型在无思维推理模式下，于多项推理基准测试中取得显著提升，证明高质量推理可通过隐式学习与执行实现，无需显式的逐步生成过程。