for step in range(num_steps):
    groups = await art.gather_trajectory_groups(
        (
            art.TrajectoryGroup(
                rollout(model, scenario) for _ in range(4)
            )
            for scenario in scenarios
        ),
        after_each=lambda g: ruler_score_group(
            g, "openai/o3"),
    )
    await model.train(groups)  # GRPO updates LoRA weights