#robustness
Every summary, chronological. Filter by category, tag, or source from the rail.
Tag · #robustness
Improving AI Agent Robustness Against Incentive-Misaligned Environments
Computer-use agents often fail to act in a user's best interest when environments are designed to steer outcomes. The CAVEAT benchmark reveals that performance drops from 78.6% to 17.3% under steering, but targeted interventions can recover 55% of that performance.
arXiv cs.AI
Showing 1 of 1