AgentsAugust 29, 2026via The Decoder
Google's WikiSkill gives AI agents a persistent memory of past mistakes to sharpen future performance
Why it matters
Agent reliability and capability just shifted. WikiSkill lets agents build and query a persistent knowledge base across runs, turning isolated trials into cumulative learning. This is infrastructure that changes how agents scale and perform in production.
Key signals
- Google Research releases WikiSkill framework
- Agents maintain persistent wiki-like knowledge base of failures and successes
- Smaller models with WikiSkill match larger models without it
- Framework enables cross-run learning instead of discarding knowledge after each execution
- Performance gains scale with model size but efficiency gains favor smaller models
The hook
Smaller models just caught up to larger ones. Google's WikiSkill gives agents persistent memory — they learn from every failure, every success.
Google Research has introduced WikiSkill, a framework that gives AI agents a persistent knowledge base. Instead of discarding what they learned after each run, agents document both failures and successes in a wiki-like structure and use that knowledge to get better over time. Larger models benefit m…