Paper 2602.10063
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
- Published
- Feb 2026
- Research lab
- Independent
- Citations
- 1
- GitHub
- 65 stars
01 In brief
Summary
The paper introduces Chain of Mindset (CoM), a training-free agentic framework for LLM reasoning that enables step-level adaptive switching among four cognitive 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 information flow to reduce interference.
CoM is evaluated on six benchmarks (AIME 2025, Real-Fermi, LiveCodeBench, GPQA-Diamond, MathVision-Mini, MAZE) using Qwen3-VL-32B-Instruct and Gemini-2.0-Flash.
It achieves state-of-the-art overall accuracy of 63.28% and 52.41%, outperforming the strongest baseline (MRP) by 4.96% and 4.72%, respectively.
Ablations show the Context Gate is most critical (removal drops overall accuracy by 8.24%), and the Divergent mindset is key for mathematical reasoning (AIME25 drops 16.66% without it).
CoM balances efficiency, using 28.4k tokens on average, and generalizes across open- and closed-source models without additional training.
The framework supports dynamic re-planning and error recovery, as illustrated in case studies.
02 From the paper
Abstract
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}.