形式追随功能:递归茎模型
Form Follows Function: Recursive Stem Model
AI总结:
递归茎模型通过改变训练方式,使网络学习稳定且深度无关的转移算子,从而提升训练效率和测试时的推理能力。
摘要:
递归推理模型如分层推理模型(HRM)和小递归模型(TRM)表明,小的、权重共享的网络可以通过迭代细化潜在状态来解决计算密集型和NP谜题,但其训练通常依赖于深度监督和/或长展开,这会增加墙钟成本并可能使模型偏向贪婪的中间行为。我们引入递归茎模型(RSM),一种递归推理方法,保持TRM风格的骨干,但改变训练合同,使网络学习一个稳定、深度无关的转移算子。RSM在训练期间完全断开隐藏状态的历史,将早期迭代视为断开的“预热”步骤,并仅在最后一步应用损失。我们进一步独立地增加外递归深度H和内计算深度L,并使用随机外转移方案(随机深度超过H)来缓解增加深度时的不稳定性。这产生了两个关键能力:(i)比TRM快超过20倍的训练,同时提高准确性(约5倍的错误率减少),(ii)测试时的扩展性,其中推理可以运行任意多的细化步骤(~20,000 H_test ≫ 20 H_train),使额外的“思考”无需重新训练。在Sudoku-Extreme上,RSM达到97.5%的精确准确度(在~1小时内训练单个A100上),在Maze-Hard(30×30)上,使用基于注意的实例化,在~40分钟内达到约80%的精确准确度。最后,由于RSM实现了迭代稳定过程,收敛行为提供了一个简单的、架构原生的可靠性信号:非稳定轨迹警告模型尚未达到可行的解决方案,可以作为防止幻觉的防护,而稳定的固定点可以与领域验证器配对进行实际的正确性检查。
英文摘要:
Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can solve compute-heavy and NP puzzles by iteratively refining latent states, but their training typically relies on deep supervision and/or long unrolls that increase wall-clock cost and can bias the model toward greedy intermediate behavior. We introduce Recursive Stem Model (RSM), a recursive reasoning approach that keeps the TRM-style backbone while changing the training contract so the network learns a stable, depth-agnostic transition operator. RSM fully detaches the hidden-state history during training, treats early iterations as detached "warm-up" steps, and applies loss only at the final step. We further grow the outer recursion depth $H$ and inner compute depth $L$ independently and use a stochastic outer-transition scheme (stochastic depth over $H$) to mitigate instability when increasing depth. This yields two key capabilities: (i) $>20\times$ faster training than TRM while improving accuracy ($\approx 5\times$ reduction in error rate), and (ii) test-time scaling where inference can run for arbitrarily many refinement steps ($\sim 20,000 H_{\text{test}} \gg 20 H_{\text{train}}$), enabling additional "thinking" without retraining. On Sudoku-Extreme, RSM reaches 97.5% exact accuracy with test-time compute (within ~1 hour of training on a single A100), and on Maze-Hard ($30 \times 30$) it reaches ~80% exact accuracy in ~40 minutes using attention-based instantiation. Finally, because RSM implements an iterative settling process, convergence behavior provides a simple, architecture-native reliability signal: non-settling trajectories warn that the model has not reached a viable solution and can be a guard against hallucination, while stable fixed points can be paired with domain verifiers for practical correctness checks.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。