reward-models
Everything on Ground Truth tagged “reward-models” — 3 items.
The AI judges grading computer-use agents are too easy on them News
A new benchmark finds that vision-language models used to grade whether a computer-use agent finished its task systematically accept failed runs as successes, and that judgment quality varies more across operating systems than across judges.
Credit assignment: figuring out which step deserved the reward Lesson
Credit assignment is the problem of working out which of an agent's many decisions actually caused the eventual outcome, and it is the central difficulty in training anything that acts over a long sequence of steps.
OS-Shepherd-9B Tool
A 9B reward model trained specifically to judge whether a computer-use agent actually finished its task, built to cut the false-success verdicts that general-purpose vision-language judges produce. A 35B sibling and the OSReward benchmark ship alongside it.