CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments
CAVEAT-Harness is developed, which targets failures and raises the optimal purchase rate by up to 80.0 percentage points, and targeted post-training further improves a smaller open model, to establish incentive robustness as a distinct challenge for delegated agents and diagnose failure modes.
Yuxuan Li, Will Epperson, W. Deng et al.
· 1 citation