[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
☆1,426Apr 17, 2026Updated last month
Alternatives and similar repositories for reasoning-gym
Users that are interested in reasoning-gym are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Our library for RL environments + evals☆4,125Updated this week
- Agentic RL Training at Scale☆1,402Updated this week
- Collection of LLM completions for reasoning-gym task datasets☆31Jul 4, 2025Updated 10 months ago
- Understanding R1-Zero-Like Training: A Critical Perspective☆1,259Aug 27, 2025Updated 9 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆21,514Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official Repo for Open-Reasoner-Zero☆2,091Jun 2, 2025Updated 11 months ago
- Democratizing Reinforcement Learning for LLMs☆5,548May 20, 2026Updated last week
- Simple RL training for reasoning☆3,859Dec 23, 2025Updated 5 months ago
- ☆1,144Jan 10, 2026Updated 4 months ago
- Minimal reproduction of DeepSeek R1-Zero☆13,104Feb 27, 2026Updated 3 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,668Apr 14, 2026Updated last month
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,867May 18, 2026Updated last week
- AllenAI's post-training codebase☆3,729Updated this week
- A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning☆398May 16, 2026Updated last week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆487Sep 27, 2024Updated last year
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆679Jul 29, 2025Updated 9 months ago
- Scalable RL solution for advanced reasoning of language models☆1,859Mar 18, 2025Updated last year
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆1,224May 18, 2026Updated last week
- A Gym for Agentic LLMs☆488Jan 21, 2026Updated 4 months ago
- Fully open data curation for reasoning models☆2,261Dec 2, 2025Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆2,698Apr 7, 2026Updated last month
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆188Jul 23, 2025Updated 10 months ago
- System 2 Reasoning Link Collection☆874Mar 16, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆414May 20, 2026Updated last week
- A bibliography and survey of the papers surrounding o1☆1,214Nov 16, 2024Updated last year
- NanoGPT (124M) in 90 seconds☆5,270May 14, 2026Updated 2 weeks ago
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆9,548Updated this week
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆657Jan 29, 2026Updated 3 months ago
- Fully open reproduction of DeepSeek-R1☆26,020Apr 2, 2026Updated last month
- Train transformer language models with reinforcement learning.☆18,411May 19, 2026Updated last week
- Synthetic data curation for post-training and structured data extraction☆1,679Apr 18, 2026Updated last month
- Automatic evals for LLMs☆596Feb 24, 2026Updated 3 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Minimalistic 4D-parallelism distributed training framework for education purpose☆2,188Aug 26, 2025Updated 9 months ago
- Scalable toolkit for efficient model reinforcement☆1,650Updated this week
- Minimal hackable GRPO implementation☆338Jan 31, 2025Updated last year
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆4,753Nov 13, 2025Updated 6 months ago
- Tools for merging pretrained large language models.☆7,100May 6, 2026Updated 3 weeks ago
- [COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents☆280Jul 13, 2025Updated 10 months ago
- A framework for few-shot evaluation of language models.☆12,678May 11, 2026Updated 2 weeks ago