Git Stars Git Stars

#reinforcement-learning-for-llms Repositories

Discover 7 active open source GitHub repositories tagged with #reinforcement-learning-for-llms, accumulating 31,786 total stars (averaging 4,540 stars per project). Leading this topic is verl-project/verl with 24,302 stars.

7
Total Repositories
31,786
Total Stars
4,540
Avg Stars/Repo
Programming Languages: Python Jupyter Notebook
1
verl-project/verl

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

verl-project
โญ 24,302 Python ๐Ÿ‘ค verl-project Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-10-31
2
policy-gradient/GRPO-Zero

Implementing DeepSeek R1's GRPO algorithm from scratch

policy-gradient
โญ 1,854 Python ๐Ÿ‘ค policy-gradient Organization ๐Ÿ• Updated 2025-04-18 ๐Ÿ“… Created 2025-04-08
3
Simple-Efficient/RL-Factory

Train your Agent model via our easy and efficient framework

Simple-Efficient
โญ 1,789 Python ๐Ÿ‘ค Simple-Efficient User ๐Ÿ• Updated 2025-12-05 ๐Ÿ“… Created 2025-05-23
4
VILA-Lab/Awesome-DLMs

The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".

VILA-Lab
โญ 1,252 ๐Ÿ‘ค VILA-Lab Organization ๐Ÿ• Updated 2026-10-02 ๐Ÿ“… Created 2025-07-14
5
SakanaAI/self-adaptive-llms

A Self-adaptation Framework๐Ÿ™ that adapts LLMs for unseen tasks in real-time!

SakanaAI
โญ 1,215 Python ๐Ÿ‘ค SakanaAI Organization ๐Ÿ• Updated 2025-01-30 ๐Ÿ“… Created 2024-12-02
6
facebookresearch/swe-rl

[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

facebookresearch
โญ 696 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2025-03-16 ๐Ÿ“… Created 2025-02-23
7
dCaples/AutoDidact

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

dCaples
โญ 689 Jupyter Notebook ๐Ÿ‘ค dCaples User ๐Ÿ• Updated 2025-03-22 ๐Ÿ“… Created 2025-03-08

Frequently Asked Questions

1

What is the most popular #reinforcement-learning-for-llms repository on GitHub?

The top ranked open source #reinforcement-learning-for-llms project on GitHub is verl-project/verl with 24,302 stars. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

2

Which programming languages are most used in #reinforcement-learning-for-llms repositories?

Among the top ranked #reinforcement-learning-for-llms projects on GitHub, the most common programming languages are Python, Jupyter Notebook.

3

How is the #reinforcement-learning-for-llms repository ranking calculated?

We track 7 active open source repositories tagged with #reinforcement-learning-for-llms (500+ stars), totaling 31,786 stars with an average of 4,540 stars per repository. Rankings update daily from the GitHub API.