Chain of Mindset: Reasoning with Adaptive Cognitive Modes

2026-02-10

AI Summary

This work addresses the limitation of current large language models, which employ fixed reasoning paradigms and struggle to adapt to the varying cognitive demands across different reasoning stages. The authors propose a training-free agent framework that decomposes reasoning into four heterogeneous cognitive modes—spatial, aggregative, divergent, and algorithmic—dynamically orchestrated by a meta-agent based on the current reasoning state. A bidirectional contextual gating mechanism efficiently coordinates information flow among these modes. This approach achieves the first dynamic collaboration of multiple cognitive modes, transcending the constraints of conventional fixed reasoning paradigms. It attains state-of-the-art performance across six benchmarks spanning mathematical reasoning, code generation, scientific question answering, and spatial reasoning, improving accuracy by 4.96% and 4.72% over Qwen3-VL-32B-Instruct and Gemini-2.0-Flash, respectively, while maintaining computational efficiency.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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}.

Problem

• reasoning
• mindset
• cognitive modes
• large language models
• adaptive reasoning

Innovation

• Chain of Mindset
• adaptive cognitive modes
• Meta-Agent
• Context Gate
• heterogeneous reasoning