Google's WikiSkill lets agents retain learned fixes, helping 9B Qwen beat 27B
tuvllms · x · 2026-10-02
Per VentureBeat, Google's WikiSkill gives AI agents a place to keep what they learned when a fix fails, beyond just having skills. In tests, a 9B Qwen with evolved skills outscored a 27B Qwen without them — suggesting persistent skill memory can outweigh raw parameter count.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16