Pass the Baton: Trajectory-Relayed On-Policy Distillation
Zhejiang University
A new on-policy distillation method where a teacher and student model relay segments of a reasoning trajectory to each other, aiming to keep the student's training distribution closer to what it will see at inference than standard full-trajectory distillation.
Why it matters
Landed on HuggingFace Daily Papers (July 29, 2026, 27 upvotes); on-policy distillation is an active area for cheaply transferring reasoning ability from large to small models.
Importance: 2/5
Incremental research contribution in an active area, modest HF Daily Papers traction (27 upvotes).
Sources
secondary
HuggingFace Daily Papers, July 29 2026