用首个响应信号决定信心，让模型更快更准地解谜题。
Speed is Confidence
- 以首个输出信号作为决策依据，减少推理步骤
- 97%准确率仅需1/10步推理，比平均概率高6个百分点
- 训练时只更新最优路径，实现高速低耗推理
生物神经系统的快速响应受能量限制，进化策略是依赖首个信号。胜者通吃电路和首次放电编码隐含将放电时间视为信心表达。本文将其应用于微型递归模型（TRM）集成。在Sudoku-Extreme数据集上，先停选择法达97%准确率，优于概率平均的91%，且推理步数减少10倍；单模型基线为85.5%±1.3%。通过维持K=4个并行隐状态，但仅对最低损失“胜者”反向传播，训练后达到96.9%±0.6%准确率，与集成性能相当，推理成本仅1倍，方差不足基线一半。诊断显示基线失败中89%为选择错误，表明99%为可达成上限。实验全程仅用一块RTX 5090，基于改进的SwiGLU使Muon模型与高学习率可行，基线训练仅48分钟，全胜者通吃（K=4）训练6小时，均在消费级硬件完成。
原文摘要 · Abstract (English)
Biological neural systems must be fast but are energy-constrained. Evolution's solution: act on the first signal. Winner-take-all circuits and time-to-first-spike coding implicitly treat when a neuron fires as an expression of confidence. We apply this principle to ensembles of Tiny Recursive Models (TRM) [Jolicoeur-Martineau et al., 2025]. On Sudoku-Extreme, halt-first selection achieves 97% accuracy vs. 91% for probability averaging -- while requiring 10x fewer reasoning steps. A single baseline model achieves 85.5% +/- 1.3%. Can we internalize this as a training-only cost? Yes: by maintaining K=4 parallel latent states but backpropping only through the lowest-loss "winner," we achieve 96.9% +/- 0.6% accuracy -- matching ensemble performance at 1x inference cost, with less than half the variance of the baseline. A key diagnostic: 89% of baseline failures are selection problems, revealing a 99% accuracy ceiling. As in nature, this work was also resource constrained: all experiments used a single RTX 5090. A modified SwiGLU [Shazeer, 2020] made Muon [Jordan et al., 2024] and high LR viable, enabling baseline training in 48 minutes and full WTA (K=4) in 6 hours on consumer hardware.
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。