Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
| Date | Stars |
|---|---|
| 2026-07-24 | 1464 |
| 2026-07-25 | 1468 |
| 2026-07-28 | 1468 |
| 2026-07-30 | 1468 |
| 2026-07-31 | 1471 |
| 2026-08-05 | 1473 |
| 2026-08-06 | 1473 |
Today
— stars today
This week
+5 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.34%/day
<p align="center">
<!-- title -->
<h1 align="center"><img src="https://github.com/open-thought/reasoning-gym/raw/main/assets/icon.png" alt="Reasoning Gym Logo" style="vertical-align: bottom;" width="54px" height="40px"> Reasoning Gym</h1>
<!-- teaser -->
<p align="center">
<img src="https://github.com/open-thought/reasoning-gym/raw/main/assets/examples.png" width="800px">
</p>
<!-- badges -->
<p align="center">
<a href="https://arxiv.org/abs/2505.24760" target="_blank" style="margin-right: 10px;">
<img src="https://img.shields.io/badge/arXiv-2505.24760-b31b1b.svg?style=for-the-badge" alt="Paper PDF">
</a>
<a href="https://discord.gg/gpumode" target="_blank">
<img src="https://dcbadge.limes.pink/api/server/gpumode?style=for-the-badge" alt="Discord Server">
</a>
</p>
</p>
## 🧠 About
**Reasoning Gym** is a community-created Python library of procedural dataset generators and algorithmically verifiable reasoning environments for training reasoning models with reinforcement learning (RL). The goal is to generate virtually infinite training data with adjustable complexity.
It currently provides **more than 100** tasks over many domains, including but not limited to _algebra_, _arithmetic_, _computation_, _cognition_, _geometry_, _graph theory_, _logic_, and many common _games_.
Some tasks have a single correct answer, while others, such as [Rubik‘s Cube](https://en.wikipedia.org/wiki/Rubik%27s_Cube) and [Countdown](<https://en.wikipedia.org/wiki/Countdown_(game_show)#Numbers_Round>), have many correct solutions. To support this, we provide a standard interface for procedurally verifying solutions.
## 🖼️ Dataset Gallery
In [GALLERY.md](https://github.com/open-thought/reasoning-gym/blob/main/GALLERY.md), you can find example outputs of all datasets available in `reasoning-gym`.
## ⬇️ Installation
The `reasoning-gym` package requires Python >= 3.10.
Install the latest published [package from PyPI](https://pypi.org/project/reasoning-gym/) via `pip`:
```
pip install reasoning-gym
```
_Note that this project is currently under active development, and the version published on PyPI may be a few days behind `main`._
## ✨ Quickstart
Starting to generate tasks using Reasoning Gym is straightforward:
```python
import reasoning_gym
data = reasoning_gym.create_dataset('leg_counting', size=10, seed=42)
for i, x in enumerate(data):
print(f'{i}: q="{x['question']}", a="{x['answer']}"')
print('metadata:', x['metadata'])
# use the dataset's `score_answer` method for algorithmic verification
assert data.score_answer(answer=x['answer'], entry=x) == 1.0
```
Output:
```
0: q="How many legs are there in total if you have 1 sea slug, 1 deer?", a="4"
metadata: {'animals': {'sea slug': 1, 'deer': 1}, 'total_legs': 4}
1: q="How many legs are there in total if you have 2 sheeps, 2 dogs?", a="16"
metadata: {'animals': {'sheep': 2, 'dog': 2}, 'total_legs': 16}
2: q="How many legs are there in total if you have 1 crab, 2 lobsters, 1 human, 1 cow, 1 bee?", a="42"
...
```
Use keyword arguments to pass task-specific configuration values:
```python
reasoning_gym.create_dataset('leg_counting', size=10, seed=42, max_animals=20)
```
Create a composite dataset containing multiple task types, with optional relative task weightings:
```python
from reasoning_gym.composite import DatasetSpec
specs = [
# here, leg_counting tasks will make up two thirds of tasks
DatasetSpec(name='leg_counting', weight=2, config={}), # default config
DatasetSpec(name='figlet_font', weight=1, config={"min_word_len": 4, "max_word_len": 6}), # specify config
]
reasoning_gym.create_dataset('composite', size=10, seed=42, datasets=specs)
```
For the simplest way to get started training models with Reasoning Gym, we recommend using the `verifiers` library, which directly supports RG tasks. See `exampleExcerpt of 8,970 characters
Read on GitHub
Andreas Köpf · PROVISIO GmbH · Germany
680
201
97
Rich Jones · Joyyo
92
Oliver Stanley · United Kingdom
81
50
21
17
15
Jean Kaddour · United Kingdom
9
8
8
7
Aayam · Oregon State University · United States
6
5
theblackcat102 · Appier AI Research · Taiwan
3
3
3
2
Prime Intellect
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9451d0283da35fa3, topic:reinforcement-learning, desc:reinforcement learning, readme:reinforcement learning
matched fp:9451d0283da35fa3, topic:large-language-models