open-thought/reasoning-gym

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

1 best points · 0 comments · 3 Hacker News posts · 1,548 GitHub stars · View on GitHub

Hacker News discussions

• Reasoning Gym: Procedural Dataset Generation for Reinforcement Learning (1 points, 0 comments, by starzmustdie, 2025-05-27)
• Reasoning Gym – Procedural RL reasoning datasets (1 points, 0 comments, by t55, 2025-07-24)
• Procedural Reasoning Datasets (1 points, 0 comments, by t55, 2025-08-05)