Google WikiSkill Shows Smaller Models Beating Larger Ones via Skill Evolution

bittingthembits · x · 2026-08-29

Google Research released WikiSkill, splitting agent intelligence into raw experience, a knowledge base, and reusable skills. Experiments show a 9B model with evolved skills scored 47.4%, beating a 27B model without skills at 39.4%. Skills transfer across model families; on ALFWorld, a skill from a 27B model boosted a 9B model to 70.2%, outperforming the 9B model's self-generated skill. This suggests performance gains come from inheriting accumulated knowledge rather than just scaling model size.

Related event: Google's WikiSkill: Persistent Knowledge Lets Small Models Beat Larger Ones(9 posts)→

Original post →

More from coding & agent

coding & agent channel →