Google's WikiSkill Framework Lets Agents Turn Experience into Reusable Skills

xiaohu · x · 2026-09-01

Google Research introduced the WikiSkill framework, designed to enable AI Agents to accumulate experiences and lessons from tasks into a persistent knowledge base (like a Wiki), thereby continuously evolving more powerful executable skills.

Core Pain Points

Existing Agent skill evolution methods primarily optimize the "current Skill" without maintaining a separate, growing knowledge base. This leads to:

Three-Layer Knowledge Architecture

WikiSkill addresses the knowledge gap with a layered workspace:

Performance

WikiSkill outperforms existing baselines on average across five test models. A 9B model with WikiSkill skills even surpasses the performance of a 27B model without skills.

Related event: Google's WikiSkill: Turning Agent Experience into a Persistent Knowledge Base(11 posts)→

Original post →

More from coding & agent

coding & agent channel →