Google WikiSkill enables agents to evolve skills via persistent knowledge
mark_k · x · 2026-08-28
Google Research introduces WikiSkill, a framework that compiles agent execution traces into persistent knowledge (a wiki) to continuously create and improve reusable agent skills. Experiments show it outperforms state-of-the-art methods, and skills transfer effectively across models, allowing smaller models with skills to outperform larger ones without them.
Related event: Google's WikiSkill Turns Agent Experience into Reusable Knowledge(4 posts)→
More from coding & agent
- Antirez Open Sources Code, Invites Agents to Use It — antirez · 2026-08-28
- DeepSeek Open Source Project Hits 200k Stars with Plugin-Based Design — omarsar0 · 2026-08-28
- Context Engineering Guide: Structuring Info for Reliable Agents — Pavan_Belagatti · 2026-08-28
- AI agents might expose sensitive data buried in Git history — doodlestein · 2026-08-28
- Using Agents and Small Models to Bootstrap Object Detection Data — vanstriendaniel · 2026-08-28
- 27B model with 5 skills outperforms expectations on healthcare workflows — Ubunta · 2026-08-28