41 lines
1.5 KiB
Markdown
41 lines
1.5 KiB
Markdown
---
|
||
title: "GRAM（Generative Recursive reAsoning Models）"
|
||
created: 2026-05-23
|
||
updated: 2026-05-23
|
||
type: concept
|
||
tags: [reasoning, recursive, generative, latent-variable]
|
||
sources: [raw/papers/gram-generative-recursive-reasoning-2026.md]
|
||
confidence: high
|
||
---
|
||
|
||
# GRAM (Generative Recursive reAsoning Models)
|
||
|
||
> 将递归潜在推理转化为概率性多轨迹计算：每个递归步采样条件转移（而非确定性更新），通过边缘化所有轨迹得到最终预测。
|
||
|
||
## 三大贡献
|
||
|
||
1. **潜在变量生成过程**：将递归推理形式化为 p(y|x)
|
||
2. **宽度推理扩展**：推理不仅通过递归深度扩展，还通过**并行轨迹采样数**扩展
|
||
3. **经验验证**：在结构化推理、多解恢复和无条件生成上超越确定性 baseline
|
||
|
||
## 架构核心
|
||
|
||
- **双层递归**：Inner loop (低层精炼) + Outer loop (supervision step 叠加)
|
||
- **随机引导**：高层更新产生确定性提议 u_t，加上随机项 eps_t -> h_t = u_t + eps_t
|
||
- **训练**：[[amortized-variational-inference]]（CE + KL divergence）
|
||
|
||
## 与现有推理方向的对比
|
||
|
||
| 方法 | 扩展维度 | 表示空间 |
|
||
|------|---------|---------|
|
||
| Chain-of-Thought | Token 序列 | 显式文本 |
|
||
| Diffusion Reasoning | 扩散步数 | 连续状态 |
|
||
| **GRAM** | **递归深度 x 轨迹宽度** | **离散潜在空间** |
|
||
|
||
## 相关概念
|
||
|
||
- [[stochastic-latent-trajectory]] — 随机轨迹
|
||
- [[inference-time-scaling]] — 推理时扩展
|
||
- [[deep-and-wide-reasoning]] — Deep & Wide
|
||
- [[gram-generative-recursive-reasoning-paper|GRAM 论文]]
|