# 生成式递归推理

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-20 08:00
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cmpeus3nt00v0sljwogt2s99r
- 原文链接：https://arxiv.org/abs/2605.19376

## AI 摘要

GRAM（生成式递归推理模型）框架将递归潜状态推理从确定性单一路径转变为概率性的多路径计算。它允许模型在推理时生成多种假设与替代解决策略，并可通过增加递归深度或并行采样来扩展计算能力。该框架通过摊销变分推断训练，形成了一个支持条件推理与无条件生成的潜变量生成模型。实验表明，GRAM在结构化推理及多解约束满足任务上优于确定性循环与递归基线模型，并具备了独立的无条件生成能力。

## 正文

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