An AI agent makes a mistake early in a task, then keeps going in the wrong direction.
Our researchers built PivotOPD to teach agents how to avoid those mistakes and recover when they happen. During training, a teacher model shows the agent a better action and how to get back on track over the next few steps.
Read the paper and watch how it works:
Agents that err early often compound the mistake. PivotOPD trains recovery with a teacher demonstrating a better action and the steps back on track, a method relevant to anyone training long-horizon agents.
