Google's WikiSkill gives AI agents a persistent memory of past mistakes to sharpen future performance
The short versionGoogle Research has introduced WikiSkill, a framework that gives AI agents a persistent knowledge base.
What happened
Google's WikiSkill changes how agents store, retrieve, and reuse knowledge across repeated tasks. Teams should test retrieval quality, rollback behavior, and memory growth before depending on it in production.
While candidate skill updates are subject to validation gating and rollback upon score degradation, the knowledge base persists and compounds across iterations. On individual benchmarks, the jumps can be bigger: Gemini-3.5-Flash climbs from 33.0 percent to 72.6 percent on LiveMath and from 50.5 percent to 76.6 percent on SpreadSheet.
Researchers evaluating Google's WikiSkill are the direct audience for Google.
Why it matters
Google's WikiSkill changes how agents store, retrieve, and reuse knowledge across repeated tasks. Teams should test retrieval quality, rollback behavior, and memory growth before depending on it in production.
Who this affects
Researchers evaluating Google's WikiSkill are the direct audience for Google.