🏆 #1,067 overall#243 of 1,378 in Language Models🔥 active this week

open-thought /reasoning-gym

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

$ git clone https://github.com/open-thought/reasoning-gym.git
GitHub social preview for open-thought/reasoning-gym
Stars
1.6K
1,553
This week
+5 ★
Forks
158
158
Language
Python
License
Apache-2.0
Created
Jan 23, 2025
1.8 years old
Last push
Nov 9, 2026
🔥 this week

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 1.5K▲ +14★ 1.6K

Categories

GitHub topics

More in Language Models

Language Models

AI4Finance-Foundation/FinGPT

▲ +43 ★ this week

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

💖 Sentiment Analysis🧠 Natural Language Processing
Jupyter NotebookMITupdated Oct 25, 2026
GitHub ↗★ 21.6K⑂ 3.1K
Language Models

OpenRLHF/OpenRLHF

▲ +13 ★ this week

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

PythonApache-2.0updated Nov 3, 2026
GitHub ↗★ 10.2K⑂ 1.1K
Language Models

langfengQ/verl-agent

▲ +18 ★ this week

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

PythonApache-2.0updated Jun 9, 2026
GitHub ↗★ 2.4K⑂ 244
Language Models

NVlabs/nano-rl

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

PythonApache-2.0updated Sep 24, 2025
GitHub ↗★ 730⑂ 31
Language Models

pat-jj/DeepRetrieval

[COLM’25] DeepRetrieval — 🔥 Training Search Agent by RLVR with Retrieval Outcome

🔍 Search & Retrieval
PythonMITupdated Oct 12, 2025
GitHub ↗★ 719⑂ 87
Language Models

ornith-ai/CUDA-L2

CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

CudaMITupdated Mar 30, 2026
GitHub ↗★ 488⑂ 34

Data from GitHub · snapshot Nov 16, 2026