跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23677 · v1

Simpler Tiny Recursive Models

首次提交 2026-11-18 09:05
版本更新 2026-11-18 09:05
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

Small models that execute deep looped computational graphs have shown great experimental results on puzzle-like problems like Sudoku, finding shortest paths through mazes, etc. The most well-known one is TRM (tiny recursive model), a simplification of HRM (hierarchical reasoning model). However, the underlying recursion is complicated and involves a high-level and a low-level state, a nested loop recursion, and the network calls with different input and output signatures depending on where we are in the loops. These mechanisms are needed to avoid memorization and overfitting. We propose STRM, a simplified design with a single state and a uniform update. STRM does not sacrifice generalization, improves training speed and final performance. Our key architectural choices that allow our simpler recursion to work are exponential moving updates on the states with varying rates that are jittered during training and readout of the solution on slow-updating channels only. We test STRM on Sudoku-Extreme, PPBench and Maze-Hard with the same data, parameters and compute as TRM: we improve over TRM by 3.83.8 points on Sudoku-Extreme and 8.48.4 points on PPBench and match it on Maze-Hard. On ARC-AGI-1 and ARC-AGI-2, STRM improves over the published TRM results by 5.45.4 and 0.50.5 points. We will release our code upon acceptance of the paper.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 09:05 · 最新观测版本

Simpler Tiny Recursive Models

Small models that execute deep looped computational graphs have shown great experimental results on puzzle-like problems like Sudoku, finding shortest paths through mazes, etc. The most well-known one is TRM (tiny recursive model), a simplification of HRM (hierarchical reasoning model). However, the underlying recursion is complicated and involves a high-level and a low-level state, a nested loop recursion, and the network calls with different input and output signatures depending on where we are in the loops. These mechanisms are needed to avoid memorization and overfitting. We propose STRM, a simplified design with a single state and a uniform update. STRM does not sacrifice generalization, improves training speed and final performance. Our key architectural choices that allow our simpler recursion to work are exponential moving updates on the states with varying rates that are jittered during training and readout of the solution on slow-updating channels only. We test STRM on Sudoku-Extreme, PPBench and Maze-Hard with the same data, parameters and compute as TRM: we improve over TRM by 3.83.8 points on Sudoku-Extreme and 8.48.4 points on PPBench and match it on Maze-Hard. On ARC-AGI-1 and ARC-AGI-2, STRM improves over the published TRM results by 5.45.4 and 0.50.5 points. We will release our code upon acceptance of the paper.

查看此版本解读 →查看此版本原文 ↗