A revolutionary 27M-parameter AI model that performs complex sequential reasoning in a single forward pass. Featuring dual recurrent modules for high level planning and sharp detail, it outperforms larger models on puzzles and maze challenges.

From the discussion on Hacker News:

Based on a quick first skim of the abstract and the introduction, the results from hierarchical reasoning (HRM) models look incredible:
> Using only 1,000 input-output examples, without pre-training or CoT supervision, HRM learns to solve problems that are intractable for even the most advanced LLMs. For example, it achieves near-perfect accuracy in complex Sudoku puzzles (Sudoku-Extreme Full) and optimal pathfinding in 30x30 mazes, where state-of-the-art CoT methods completely fail (0% accuracy). In the Abstraction and Reasoning Corpus (ARC) AGI Challenge 27,28,29 - a benchmark of inductive reasoning - HRM, trained from scratch with only the official dataset (~1000 examples), with only 27M parameters and a 30x30 grid context (900 tokens), achieves a performance of 40.3%, which substantially surpasses leading CoT-based models like o3-mini-high (34.5%) and Claude 3.7 8K context (21.2%), despite their considerably larger parameter sizes and context lengths, as shown in Figure 1.

Love the multi-level reasoning approach—mimicking how brains plan is such a smart move, tbh. Can’t wait to see this in action, realy cool idea!

Love how this model mimics human-like multi-level reasoning—feels like a real step up from flat AI logic, tbh. Super clever stuff here!

No way, brain-inspired reasoning in AI? That's wild! My project planning always gets messy—if this model can actually handle multi-level logic, I’m totally in. How does it scale with complexity?

From the discussion on Hacker News:

Based on a quick first skim of the abstract and the introduction, the results from hierarchical reasoning (HRM) models look incredible:
> Using only 1,000 input-output examples, without pre-training or CoT supervision, HRM learns to solve problems that are intractable for even the most advanced LLMs. For example, it achieves near-perfect accuracy in complex Sudoku puzzles (Sudoku-Extreme Full) and optimal pathfinding in 30x30 mazes, where state-of-the-art CoT methods completely fail (0% accuracy). In the Abstraction and Reasoning Corpus (ARC) AGI Challenge 27,28,29 - a benchmark of inductive reasoning - HRM, trained from scratch with only the official dataset (~1000 examples), with only 27M parameters and a 30x30 grid context (900 tokens), achieves a performance of 40.3%, which substantially surpasses leading CoT-based models like o3-mini-high (34.5%) and Claude 3.7 8K context (21.2%), despite their considerably larger parameter sizes and context lengths, as shown in Figure 1.

Love the multi-level reasoning approach—mimicking how brains plan is such a smart move, tbh. Can’t wait to see this in action, realy cool idea!

Love how this model mimics human-like multi-level reasoning—feels like a real step up from flat AI logic, tbh. Super clever stuff here!

No way, brain-inspired reasoning in AI? That's wild! My project planning always gets messy—if this model can actually handle multi-level logic, I’m totally in. How does it scale with complexity?

Hierarchical Reasoning Model

Brain-inspired, multi-level reasoning & planning AI model

Brain-inspired, multi-level reasoning & planning AI model