WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Published
Source
arXiv
Paper number
1038
Field
AI / General
arXiv ID
2608.27454

Key points

  • It separated execution traces, knowledge, and skills into three layers, with a wiki layer that continuously accumulates information and is never reset.
  • It enabled stable evolution through gating that accepts only skill changes that improve validation performance and rolls back changes that make it worse.
  • It consistently outperformed existing skill-evolution methods across 5 benchmarks (math, search, spreadsheets, document QA, and household-environment tasks) and 5 models.
  • Skill evolution had a larger effect on larger models: in the Qwen family, 4B/9B/27B models improved by an average of +12.3/+17.5/+23.9%, respectively.
  • The 9B model + WikiSkill (47.4%) beat the 27B model without skills (39.4%), and skills evolved by another model sometimes outperformed a model's own skills.
  • Performance declined in an ablation that removed the wiki, confirming that knowledge accumulation is central to the effect.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)