让大模型自动选快慢思维，平衡推理效果与算力消耗。
DynamicMind: A Tri-Mode Thinking System for Large Language Models
- 引入快、常、慢三模式思维系统，自主匹配任务复杂度。
- 提出思维密度指标，实现计算资源与问题难度精准匹配。
- 适合追求高效推理的大模型应用，尤其数学与常识问答场景。
当前大语言模型在面对不同复杂度的任务时，难以动态调整推理深度，导致性能不佳或资源浪费。为此，我们提出DynamicMind——一种新型三模式思维系统。该系统通过受认知启发的提示工程，使大模型在零样本问答任务中可自主选择快速、常规或缓慢思维模式。核心创新包括：(1) 将经典的双进程思维框架扩展为包含常规思维模式的三模式体系，以保留大模型固有能力；(2) 提出思维密度（Thinking Density）指标，实现计算资源分配与问题复杂度对齐；(3) 构建了思维模式容量（TMC）数据集及轻量级思维路由器，用于预测最优思维模式。在多个数学、常识与科学问答基准上的大量实验表明，DynamicMind不仅显著提升零样本问答性能，还实现了性能与计算效率之间的有效权衡。
原文摘要 · Abstract (English)
Modern large language models (LLMs) often struggle to dynamically adapt their reasoning depth to varying task complexities, leading to suboptimal performance or inefficient resource utilization. To address this, we introduce DynamicMind, a novel tri-mode thinking system. DynamicMind empowers LLMs to autonomously select between Fast, Normal, and Slow thinking modes for zero-shot question answering (ZSQA) tasks through cognitive-inspired prompt engineering. Our framework's core innovations include: (1) expanding the established dual-process framework of fast and slow thinking into a tri-mode thinking system involving a normal thinking mode to preserve the intrinsic capabilities of LLM; (2) proposing the Thinking Density metric, which aligns computational resource allocation with problem complexity; and (3) developing the Thinking Mode Capacity (TMC) dataset and a lightweight Mind Router to predict the optimal thinking mode. Extensive experiments across diverse mathematical, commonsense, and scientific QA benchmarks demonstrate that DynamicMind achieves superior ZSQA capabilities while establishing an effective trade-off between performance and computational efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。