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:
- Experience is hard to reuse across different rounds.
- The value of failed modifications is easily lost.
- Skills become bloated as they bear too much responsibility (saving both experience and execution rules).
Three-Layer Knowledge Architecture
WikiSkill addresses the knowledge gap with a layered workspace:
- Raw Layer: Saves complete execution trajectories as immutable evidence.
- Wiki Layer: Saves understanding by organizing common patterns from trajectories into independent pages.
- Skills Layer: Saves action rules for the executing Agent, which remain traceable to underlying evidence.
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.
More from coding & agent
- Introducing Loupe: An open-source PR review agent — andersonbcdefg · 2026-09-01
- Why "it feels better" isn't good enough for production LLM decisions — camerongreen95 · 2026-09-01
- Hermes Agent monitors chats and emails to auto-create tasks and draft work — intellectronica · 2026-09-01
- Free Australian business-day MCP server released — Impossible_Bit_2676 · 2026-09-01
- If starting with AI agents today, what would you automate first? — omnidimension85 · 2026-09-01
- SparkLLM open-sources X2.5 4B/1.7B on-device models with native 1M-token context — vllm_project · 2026-09-01