Researchers at Unknown
Proposed Hierarchical Reasoning Model (HRM) for puzzle tasks in 2025
How media typically covers Wang et al.
Research or work cited
Tiny Recursive Model (TRM) with only 7M parameters achieves 45% accuracy on ARC-AGI-1 and outperforms much larger LLMs like Deepseek R1 and o3-mini using less than 0.01% of their parameters.
“Proposed Hierarchical Reasoning Model (HRM) for puzzle tasks in 2025”