sapientinc/HRM
Hierarchical Reasoning Model Official Release
This project offers an advanced AI model designed to solve complex logical puzzles and planning challenges efficiently. It takes in structured problem data, like Sudoku grids or maze layouts, and outputs optimal solutions without needing extensive prior training examples. This is useful for researchers and practitioners working on artificial intelligence problems that require sequential reasoning and robust problem-solving.
12,358 stars. No commits in the last 6 months.
Use this if you need an AI that can solve intricate reasoning tasks, such as complex Sudoku puzzles or pathfinding in mazes, with minimal training data and high computational efficiency.
Not ideal if you are looking for a simple, off-the-shelf solution that doesn't require setting up a PyTorch and CUDA environment or if your problems are not related to abstract logical reasoning.
Stars
12,358
Forks
1,801
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sapientinc/HRM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models
HKUDS/LightReasoner
"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"