SCALE gives long agent tasks step-level credit, lifting success by up to 4.1 points
In long agent tasks, training usually only learns whether the whole attempt succeeded, which makes it hard to tell which steps helped. SCALE adds a critic that predicts, at each step, the chance the task will still be completed, and turns changes in that chance into credit for individual actions. Across five agent benchmarks and three model backbones, it beat the compared reinforcement learning baselines in most settings, with gains of up to 4.1 percentage points.