rStar-RL/LoongRL
LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts (ICLR 2026 Oral)
This project helps large language models (LLMs) understand and answer questions from very long texts, and solve complex math problems more effectively. It takes in existing LLMs and training data to produce models that can reason better over extensive documents or complex mathematical challenges. Scientists, data engineers, or machine learning researchers who work with advanced LLM development would use this.
Use this if you need to train or fine-tune large language models to excel at understanding information spread across very long documents or to solve advanced mathematical reasoning tasks with high accuracy.
Not ideal if you are looking for an out-of-the-box LLM application or if your primary need is for basic, short-context text generation rather than deep reasoning over long inputs.
Stars
13
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rStar-RL/LoongRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild