arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10063cs.AI
收藏

思维链:具有适应性认知模式的推理

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

PKU(北京大学);BJTU(北京理工大学);StepFun;SUFE(上海财经大学);NUS(新加坡国立大学);CityUHK(香港城市大学);QuantaAlpha(量子阿尔法)

Tianyi Jiang, Arctanx An, Hengyi Feng, Naixin Zhai, Haodong Li, Xiaomin Yu, Jiahui Liu, Hanwen Du, Shuo Zhang, Zhi Yang, Jie Huang, Youhua Li, Yongxin Ni, Huacan Wang, Ronghao Chen

AI总结:

本文提出Chain of Mindset框架,通过动态选择不同认知模式提升推理效率,实验显示在多个基准测试中表现优异,准确率超越基线模型。

摘要:

人类解决问题并非单一认知模式的重复,而是整合多种认知模式。现有LLM推理方法固定单一认知模式,限制了智能发展。本文提出Chain of Mindset框架,分解推理为四种功能各异的认知模式:空间、收敛、发散和算法。Meta-Agent根据推理状态动态选择最优模式,双向上下文门控过滤跨模块信息流。实验表明,CoM在数学、代码生成、科学问答和空间推理等六个挑战性基准测试中达到SOTA性能,准确率超越基线模型4.96%和4.72%。代码已公开在https://github.com/QuantaAlpha/chain-of-mindset。

英文摘要:

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}.

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。

↑