D-Skill: Distilling Teacher Knowledge through Agent Skills
Frontier language-model agents excel at complex tasks, but high inference costs make transferring their capabilities to smaller models essential. Traditional knowledge distillation achieves this through parameter updates, requiring access to the student's weights and additional training compute…
By Shuo Yuan, Dacheng Li, Joseph E. GonzalezarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 22, 2026.
Comments
Sign in to join the discussion.