Jul 2026
Multi-Turn On-Policy Distillation with Prefix Replay
ReOPD turns expensive agent-environment interaction into a reusable offline resource, enabling scalable distillation across tools, tasks, and environments and preserves or improves OPD-level accuracy, uses zero tool calls during student training, and is at least 4$\times faster per rollout than OPD.
Baohao Liao, Hanze Dong, C. Monz et al.
· arXiv.org · 7 citations
· ⚡1