让大模型按每步难度自动切换推理模式，提升效率与准确率
PATS: Process-Level Adaptive Thinking Mode Switching
- 基于步骤难度动态调整推理策略，而非整体固定模式
- 数学基准测试中高精度且仅使用中等数量的词元
- 适合追求高效推理的大模型应用开发人员
当前大型语言模型通常对所有问题采用固定推理策略，无论难易程度如何。这种忽视任务与推理过程复杂性差异的做法，导致性能与效率失衡。现有方法尝试实现无需训练的快慢思维模式切换，但受限于粗粒度的解级策略调整。为此，我们提出一种新型推理范式：过程级自适应思维模式切换（PATS），使大模型能根据每一步的难度动态调整推理策略，优化准确率与计算效率的平衡。该方法结合过程奖励模型（PRMs）与束搜索，引入渐进式模式切换和差步惩罚机制。在多个数学基准上的实验表明，该方法在保持适中词元消耗的同时实现了高准确率。本研究强调了过程级、难度感知推理策略适应的重要性，为大模型高效推理提供了重要启示。
原文摘要 · Abstract (English)
Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty. This neglect of variation in task and reasoning process complexity leads to an imbalance between performance and efficiency. Existing methods attempt to implement training-free fast-slow thinking system switching to handle problems of varying difficulty, but are limited by coarse-grained solution-level strategy adjustments. To address this issue, we propose a novel reasoning paradigm: Process-Level Adaptive Thinking Mode Switching (PATS), which enables LLMs to dynamically adjust their reasoning strategy based on the difficulty of each step, optimizing the balance between accuracy and computational efficiency. Our approach integrates Process Reward Models (PRMs) with Beam Search, incorporating progressive mode switching and bad-step penalty mechanisms. Experiments on diverse mathematical benchmarks demonstrate that our methodology achieves high accuracy while maintaining moderate token usage. This study emphasizes the significance of process-level, difficulty-aware reasoning strategy adaptation, offering valuable insights into efficient inference for LLMs.
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。