Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a single mindset; instead, we integrate multiple mindsets within the single solution process. However, existing LLM reasoning methods fall into a common trap: they apply the same fixed mindset across all steps, overlooking that different stages of solving the same problem require fundamentally different mindsets. This single-minded assumption prevents models from reaching the next level of intelligence. To address this limitation, we propose Chain of Mindset (CoM), a training-free agentic framework that enables step-level adaptive mindset orchestration. CoM decomposes reasoning into four functionally heterogeneous mindsets: Spatial, Convergent, Divergent, and Algorithmic. A Meta-Agent dynamically selects the optimal mindset based on the evolving reasoning state, while a bidirectional Context Gate filters cross-module information flow to maintain effectiveness and efficiency. Experiments across six challenging benchmarks spanning mathematics, code generation, scientific QA, and spatial reasoning demonstrate that CoM achieves state-of-the-art performance, outperforming the strongest baseline by 4.96\% and 4.72\% in overall accuracy on Qwen3-VL-32B-Instruct and Gemini-2.0-Flash, while balancing reasoning efficiency. Our code is publicly available at \href{https://github.com/QuantaAlpha/chain-of-mindset}{https://github.com/QuantaAlpha/chain-of-mindset}.

翻译：人类解决问题从来不是单一思维模式的重复，这里思维模式指的是一种独特的认知处理方式。在处理具体任务时，我们并非依赖单一的思维模式，而是在单一求解过程中整合多种思维模式。然而，现有的大语言模型推理方法陷入了一个共同的陷阱：它们在所有步骤中应用相同且固定的思维模式，忽视了解决同一问题的不同阶段需要根本不同的思维模式。这种单一思维的假设阻碍了模型达到更高层次的智能。为应对这一局限，我们提出了思维链（CoM），一种无需训练的主体性框架，能够实现步骤级别的自适应思维模式编排。CoM将推理分解为四种功能异构的思维模式：空间型、聚合型、发散型和算法型。一个元代理根据演化的推理状态动态选择最优思维模式，同时一个双向上下文门控器过滤跨模块信息流，以保持有效性和效率。在涵盖数学、代码生成、科学问答和空间推理的六个具有挑战性的基准测试上的实验表明，CoM实现了最先进的性能，在Qwen3-VL-32B-Instruct和Gemini-2.0-Flash上的整体准确率分别比最强基线高出4.96%和4.72%，同时兼顾了推理效率。我们的代码已在\href{https://github.com/QuantaAlpha/chain-of-mindset}{https://github.com/QuantaAlpha/chain-of-mindset}公开。