Multi-Signal Control

As AI models become more capable, monitoring protocols that push the safety-usefulness Pareto frontier become increasingly relevant for robust AI control. Ensemble-based AI solutions have demonstrated improved predictive power across various domains, suggesting that existing monitoring approaches could be combined to yield safer and more useful control. We investigate ensemble-based protocols using the backdoor-augmented APPS dataset in Control Arena. We find that: (1) ensemble-based approaches outperform any single monitor; (2) ensembling the three best-performing individual monitors achieved comparable performance to averaging over all monitors, indicating that understanding individual monitor performance enables less costly protocols; and (3) fine-tuning a code analysis monitor on the APPS dataset performed perfectly on the BigCodeBench dataset, suggesting strong generalization. Overall, these results demonstrate the potential for ensemble-based monitoring protocols to advance control to be both safer and more useful.