NVIDIA, Princeton and UMD introduce PivotOPD, a distillation method for multi-turn AI agents

AINVIDIA, Princeton University, and the University of Maryland introduced PivotOPD, an on-policy distillation method that teaches multi-turn LLM agents to recover from their most damaging early mistake. Tested on Qwen3-1.7B and Qwen3-8B students, it posts the best average against 13 baselines on ALFWorld, WebShop, and Search-based QA. It recovers from 72.7% of replayed pivotal mistakes, versus 20.3% for standard OPD, with no added inference cost.

AINVIDIA researchers built PivotOPD, a training method that helps AI agents avoid early mistakes and recover when they occur. During training, a teacher model shows the agent a better action and guides it back on track over the next few steps.