A 7-million parameter model outperforming models a thousand times its size on tasks like ARC Prize. ...
- 递归机制在推理阶段动态增加计算深度，突破标准LLM的固定上下文与浅层推理瓶颈。
- HRM通过外循环迭代调用基础模型实现多步推理，TRM则依赖训练中收敛的不动点递归结构。
- 小参数递归模型在ARC Prize等符号推理任务上显著优于同等规模非递归模型，验证‘计算深度’比‘参数规模’更关键。
结构提纲
按章节快速跳转。
指出700万参数模型在ARC Prize上超越千倍参数大模型，引出递归推理的核心价值。
解释标准LLM因前向单次计算导致的推理深度天花板，递归如何通过迭代调用解锁深度计算。
HRM复用轻量基础模型，在推理时通过显式外循环展开多步推理，支持可控、可解释的步骤生成。
TRM在训练中学习稳定递归映射，推理时通过迭代收敛至不动点，隐式实现深度推理。
HRM/TRM在ARC Prize等需符号操作与分步验证的任务上大幅领先，但在语言生成类任务中无明显优势。
探讨将递归机制嫁接至大规模基础模型（如Llama、Phi）以兼顾泛化力与强推理能力。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- 递归AI模型（HRM/TRM）
- 核心动机
- 突破LLM推理深度瓶颈
- 降低参数规模，提升推理效率
- HRM
- 外循环架构
- 显式多步调用基础模型
- 高可控性与可解释性
- TRM
- 不动点训练范式
- 隐式迭代收敛
- 端到端可微优化
金句 / Highlights
值得收藏与分享的关键句。
A 7-million parameter model outperforming models a thousand times its size on tasks like ARC Prize. That's what recursive reasoning unlocks.
Standard LLMs hit a fundamental ceiling on certain reasoning tasks — recursion at inference time gives small models the compute depth to break through it.
HRM uses an outer loop that repeatedly calls a base model; TRM trains a model to converge to a fixed point via iterative application.
The key insight is not more parameters, but more *compute depth* — achieved not by bigger models, but by smarter use of inference-time computation.
In this episode of Decoded, YC's @agupta and @FrancoisChauba1 break down two recent papers on recursive AI models, HRMs and TRMs, that are https://t.co/slZh2sfHlE" / X
A 7-million parameter model outperforming models a thousand times its size on tasks like ARC Prize. That's what recursive reasoning unlocks. In this episode of Decoded, YC's
and
break down two recent papers on recursive AI models, HRMs and TRMs, that are achieving state-of-the-art results with a fraction of the parameters of today's largest models. They explain why standard LLMs hit a fundamental ceiling on certain reasoning tasks, how recursion at inference time gives small models the compute depth to break through it, and what happens when you combine these ideas with the power of large-scale foundation models. 00:35 - Model Foundations 01:15 - RNN Limits and LLM Contrast 02:36 - Reasoning Limits and Sorting Analogy 04:22 - HRM Paper Introduction 05:25 - HRM Architecture and Intuition 07:36 - HRM Results and Outer Loop 09:46 - TRM Paper Overview 11:20 - TRM Training and Fixed Point 13:30 - Detailed HRM Summary 20:46 - Comparing HRM and TRM 34:45 - Future Outlook
问问这篇内容
回答仅基于本篇材料Skill 包
领域模板，一键产出结构化笔记投融资雷达包
把一条融资 / 创投新闻整理成投资人视角的雷达卡：交易要点、判断、竞争格局、风险、尽调清单。
- · 交易要点（公司 / 轮次 / 金额 / 投资人 / 估值，材料未明示则写 “未披露”）
- · 投资 thesis（这家公司为什么值得关注）
- · 竞争格局与替代方案