Introducing OpenReward - General Reasoning

General Reasoning is a London-based AI R&D company focused on building infrastructure for long horizon AI capabilities. As AI agents become more capable, they need reinforcement learning (RL) environments where they can learn, experiment, and improve over long time horizons. Yet running RL environments at scale is challenging: billions of tool calls, long trajectories and huge costs. OpenReward changes that. We make infrastructure simple and RL environments open and sharable, so that anyone can build, run and scale RL environment systems.