Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.10063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918394994884608 |
|---|---|
| author | Jiang, Tianyi An, Arctanx Feng, Hengyi Zhai, Naixin Li, Haodong Yu, Xiaomin Liu, Jiahui Du, Hanwen Zhang, Shuo Yang, Zhi Huang, Jie Li, Youhua Ni, Yongxin Wang, Huacan Chen, Ronghao |
| author_facet | Jiang, Tianyi An, Arctanx Feng, Hengyi Zhai, Naixin Li, Haodong Yu, Xiaomin Liu, Jiahui Du, Hanwen Zhang, Shuo Yang, Zhi Huang, Jie Li, Youhua Ni, Yongxin Wang, Huacan Chen, Ronghao |
| contents | 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}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_10063 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Chain of Mindset: Reasoning with Adaptive Cognitive Modes Jiang, Tianyi An, Arctanx Feng, Hengyi Zhai, Naixin Li, Haodong Yu, Xiaomin Liu, Jiahui Du, Hanwen Zhang, Shuo Yang, Zhi Huang, Jie Li, Youhua Ni, Yongxin Wang, Huacan Chen, Ronghao Artificial Intelligence 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}. |
| title | Chain of Mindset: Reasoning with Adaptive Cognitive Modes |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.10063 |