生成式递归推理

摘要

未来的神经推理系统应如何实现扩展计算？递归推理模型（RRMs）通过使用共享转移函数进行迭代潜在状态细化，为自回归序列扩展提供了一种有前景的替代方案。然而，现有的RRMs在很大程度上是确定性的，遵循单一潜在轨迹并收敛到单一预测。我们提出生成式递归推理模型（GRAM），该框架将递归潜在推理转化为概率性多轨迹计算。GRAM将推理建模为随机潜在轨迹，支持多个假设、备选解决策略，并通过递归深度和并行轨迹采样实现推理时扩展。由此得到一个潜变量生成模型，可通过p_θ(y | x)进行条件推理，并在输入固定或缺失的情况下通过p_θ(x)进行无条件生成。通过摊销变分推断进行训练后，GRAM在结构化推理和多解约束满足任务上优于确定性递归和循环基线方法，并展现出无条件生成能力。https://ahn-ml.github.io/gram-website

English

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared transition functions. Yet existing RRMs are largely deterministic, following a single latent trajectory and converging to a single prediction. We introduce Generative Recursive reAsoning Models (GRAM), a framework that turns recursive latent reasoning into probabilistic multi-trajectory computation. GRAM models reasoning as a stochastic latent trajectory, enabling multiple hypotheses, alternative solution strategies, and inference-time scaling through both recursive depth and parallel trajectory sampling. This yields a latent-variable generative model supporting conditional reasoning via p_θ(y mid x) and, with fixed or absent inputs, unconditional generation via p_θ(x). Trained with amortized variational inference, GRAM improves over deterministic recurrent and recursive baselines on structured reasoning and multi-solution constraint satisfaction tasks, while demonstrating an unconditional generation capability. https://ahn-ml.github.io/gram-website