Unreasonable Scaling Computer Use Agents

Scale computer-use agents from 30% to 72% success rate by generating parallel rollouts and selecting best trajectories through behavior narrative evaluation. Use when deploying desktop agents on complex, high-variance task scenarios.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit a98f84ca4f

Frequently asked questions

npx get-skill add adu2021/unreasonable-scaling-computer-use-agents