软性思维：在连续概念空间中释放大语言模型的推理潜能

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space

May 21, 2025

作者: Zhen Zhang, Xuehai He, Weixiang Yan, Ao Shen, Chenyang Zhao, Shuohang Wang, Yelong Shen, Xin Eric Wang

cs.AI

摘要

人类认知通常涉及对抽象、流动概念的思考，而非严格依赖离散的语言符号。然而，当前的推理模型局限于人类语言的边界内，处理代表语义空间中固定点的离散符号嵌入。这种离散性限制制约了此类推理模型的表达能力和上限潜力，常常导致推理路径的探索不完整，因为标准的思维链（CoT）方法依赖于每一步采样一个符号。在本研究中，我们提出了“软思考”方法，这是一种无需训练的技术，通过在连续概念空间中生成柔软、抽象的概念符号，来模拟人类“软”推理。这些概念符号由符号嵌入的概率加权混合构成，形成了连续的概念空间，实现了平滑过渡和超越传统离散边界的更丰富表示。本质上，每个生成的概念符号封装了来自相关离散符号的多种含义，隐式地探索了多种推理路径，从而有效收敛至正确答案。在多样化的数学和编程基准测试中，实证评估一致证明了“软思考”的有效性和效率，与标准CoT相比，pass@1准确率最高提升2.48个百分点，同时符号使用量最多减少22.4%。定性分析进一步显示，“软思考”的输出保持高度可解释性和可读性，凸显了其突破基于离散语言推理固有瓶颈的潜力。代码已发布于https://github.com/eric-ai-lab/Soft-Thinking。

English

Human cognition typically involves thinking through abstract, fluid concepts rather than strictly using discrete linguistic tokens. Current reasoning models, however, are constrained to reasoning within the boundaries of human language, processing discrete token embeddings that represent fixed points in the semantic space. This discrete constraint restricts the expressive power and upper potential of such reasoning models, often causing incomplete exploration of reasoning paths, as standard Chain-of-Thought (CoT) methods rely on sampling one token per step. In this work, we introduce Soft Thinking, a training-free method that emulates human-like "soft" reasoning by generating soft, abstract concept tokens in a continuous concept space. These concept tokens are created by the probability-weighted mixture of token embeddings, which form the continuous concept space, enabling smooth transitions and richer representations that transcend traditional discrete boundaries. In essence, each generated concept token encapsulates multiple meanings from related discrete tokens, implicitly exploring various reasoning paths to converge effectively toward the correct answer. Empirical evaluations on diverse mathematical and coding benchmarks consistently demonstrate the effectiveness and efficiency of Soft Thinking, improving pass@1 accuracy by up to 2.48 points while simultaneously reducing token usage by up to 22.4% compared to standard CoT. Qualitative analysis further reveals that Soft Thinking outputs remain highly interpretable and readable, highlighting the potential of Soft Thinking to break the inherent bottleneck of discrete language-based reasoning. Code is available at https://github.com/eric-ai-lab/Soft-Thinking.