通过二维探测提升并行推理效率，减少计算开销。
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
- 周期性获取分支中间答案，捕捉宽度与深度动态。
- 比标准多数投票少用35.8%串行token，总成本降25.8%以上。
- 无需训练，适合高精度推理场景优化资源使用。
并行推理虽具潜力，但计算开销大。现有方法依赖局部信号，缺乏对分支间全局动态的建模。本文提出2D探测机制，通过周期性获取所有分支的中间答案，揭示宽度-深度分配的非单调缩放、分支长度异质性及全局共识早期稳定等规律。基于此，提出无需训练的Parallel-Probe控制器：利用共识实现早期停止以控制推理深度，通过偏差判别进行分支剪枝以动态调整宽度。在三个基准和多个模型上的实验表明，Parallel-Probe在测试时扩展上建立更优帕累托前沿。相比标准多数投票，其串行token减少最多35.8%，总token成本降低超25.8%，且保持竞争性准确率。
原文摘要 · Abstract (English)
Parallel thinking has emerged as a promising paradigm for reasoning, yet it imposes significant computational burdens. Existing efficiency methods primarily rely on local, per-trajectory signals and lack principled mechanisms to exploit global dynamics across parallel branches. We introduce 2D probing, an interface that exposes the width-depth dynamics of parallel thinking by periodically eliciting intermediate answers from all branches. Our analysis reveals three key insights: non-monotonic scaling across width-depth allocations, heterogeneous reasoning branch lengths, and early stabilization of global consensus. Guided by these insights, we introduce $\textbf{Parallel-Probe}$, a training-free controller designed to optimize online parallel thinking. Parallel-Probe employs consensus-based early stopping to regulate reasoning depth and deviation-based branch pruning to dynamically adjust width. Extensive experiments across three benchmarks and multiple models demonstrate that Parallel-Probe establishes a superior Pareto frontier for test-time scaling. Compared to standard majority voting, it reduces sequential tokens by up to $\textbf{35.8}$% and total token cost by over $\textbf{25.8}$% while maintaining competitive accuracy.
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。