open-thought/reasoning-gym

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

LLM & foundation modelsPython Apache-2.0 157created 2025-01-23

Stars

1,550

1-day growth

—

7-day growth

—

30-day growth

—

Star history

Tracked since 2026-11-13

The chart appears after at least 2 days of data.

#gym#large-language-models#reinforcement-learning

Top contributors

Not collected yet (contributors job).

open-thought/reasoning-gym · AI Repo Stats