summaries2 min read
Peking University Distills Agent Harness Into Model, Lifting Task Success by 21 Points
A Peking University team fine tuned Qwen3.5 9B on “corrected runs” and found the distilled model beat the original model plus harness setup, raising average task success by 21 points.
By O'Reilly MediaZetik Blog

Read the full story
Originally published by Zetik Blog on Oct 27, 2026.
Comments
Sign in to join the discussion.