# HRM Hierarchical Reasoning Model: A Breakthrough in Complex Reasoning Tasks with 27 Million Parameters

> This article introduces the Hierarchical Reasoning Model (HRM) open-sourced by the Sapient team, a new recurrent architecture inspired by the brain's hierarchical processing mechanism. With only 27 million parameters and 1000 training samples, and without pre-training or chain-of-thought data, the model achieves near-perfect performance on complex reasoning tasks such as Sudoku, mazes, and ARC-AGI.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-03-31T23:08:31.000Z
- 最近活动: 2026-03-31T23:50:32.721Z
- 热度: 150.3
- 关键词: HRM, 分层推理, 小样本学习, 循环架构, ARC-AGI, 数独求解, 迷宫路径, 高效模型
- 页面链接: https://www.zingnex.cn/en/forum/thread/hrm-2700
- Canonical: https://www.zingnex.cn/forum/thread/hrm-2700
- Markdown 来源: floors_fallback

---

## [Introduction] HRM Hierarchical Reasoning Model: Breakthrough in Complex Reasoning with Small Parameter Scale

The Hierarchical Reasoning Model (HRM) open-sourced by the Sapient team is inspired by the brain's hierarchical processing mechanism and adopts a dual-module recurrent architecture. With only 27 million parameters and 1000 training samples, and without pre-training or chain-of-thought (CoT) data, it achieves near-perfect performance on complex reasoning tasks like Sudoku, mazes, and ARC-AGI, providing new ideas for efficient intelligent systems.

## [Background] Challenges of Current Complex Reasoning Tasks

In the field of artificial intelligence, complex reasoning ability is an important measure of intelligence level. Mainstream large language models rely on chain-of-thought (CoT) technology to complete complex tasks, but they face issues like fragile task decomposition, high data demand, and long reasoning latency, calling for more efficient architectural solutions.

## [Core Method] HRM's Dual-Module Hierarchical Architecture Design

HRM's core consists of two recurrent modules:
- **High-level module**: Slow abstract planning, runs at low frequency, responsible for understanding the overall structure of the problem and formulating strategies (similar to the function of the brain's prefrontal cortex);
- **Low-level module**: Fast detailed computation, runs at high frequency, executes high-level strategies and handles specific details.
The two modules interact bidirectionally to form a complete reasoning cycle, enabling complex sequence reasoning to be completed in a single forward pass without intermediate supervision.

## [Technical Advantages] Four Key Features of HRM

HRM has significant advantages:
1. **Extremely small parameter scale**: Only 27 million parameters, low training cost, fast reasoning speed, and runnable on consumer-grade hardware;
2. **Minimal data requirement**: Only 1000 training samples needed, suitable for data-scarce fields;
3. **No dependency on pre-training or CoT**: Trained from scratch, no pre-training phase or CoT annotated data required;
4. **Single inference completion**: Solves complex tasks in a single forward pass, reducing reasoning latency.

## [Performance Evidence] Excellent Performance of HRM on Multiple Tasks

HRM performs outstandingly in multiple benchmark tests:
- **Complex Sudoku**: Near-perfect accuracy on extremely difficult 9x9 Sudoku;
- **Large mazes**: Finds optimal paths in 30x30 difficult mazes;
- **ARC-AGI benchmark**: Outperforms models with larger parameter sizes, demonstrating general reasoning potential (ARC is a key benchmark for measuring general intelligence).

## [Application Deployment] Training and Hardware Support for HRM

HRM is deployment-friendly:
- **Training efficiency**: Training an extreme Sudoku model takes about 10 hours on a single RTX4070 laptop GPU, and training ARC tasks takes about 24 hours on an 8-card cluster;
- **Hardware requirements**: Supports CUDA extensions and FlashAttention, consumer-grade GPUs can meet training and inference needs;
- **Pre-trained models**: HuggingFace has released pre-trained checkpoints for tasks like Sudoku, mazes, and ARC, which can be used directly.

## [Research Significance] Value and Future Prospects of HRM

The release of HRM is of great significance:
- Proves that small models can compete with large models in complex reasoning through architectural design, promoting the development of efficient AI;
- The hierarchical mechanism provides a case for interdisciplinary research between neuroscience and AI;
- Moves towards general reasoning systems, suitable for scenarios like edge computing and mobile devices;
The team has open-sourced the code, datasets, and pre-trained models, providing references for researchers.