LLM360/Reasoning360
A repo for open research on building large reasoning models
This project offers tools and pipelines for researchers who want to build and refine large language models (LLMs) specifically for complex reasoning tasks across multiple domains. It takes in specialized datasets, like the 'Guru RL data', and helps train models to produce more accurate and nuanced reasoning outputs. The primary users are AI/ML researchers focused on advancing LLM capabilities.
140 stars.
Use this if you are an AI researcher developing advanced large language models and want to experiment with reinforcement learning to enhance their reasoning abilities across diverse problem sets.
Not ideal if you are an end-user looking for a ready-to-use LLM for general tasks or if you lack a deep understanding of machine learning model training and infrastructure.
Stars
140
Forks
17
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/LLM360/Reasoning360"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
open-thought/reasoning-gym
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Hmbown/Hegelion
Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
TsinghuaC3I/Awesome-RL-for-LRMs
A Survey of Reinforcement Learning for Large Reasoning Models
bowang-lab/BioReason
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
Peiyang-Song/Awesome-LLM-Reasoning-Failures
Repo for "Large Language Model Reasoning Failures"