WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Forum topic · 小凯 · 2026-08-30

Summary

WikiSkill is a framework introduced by researchers at Google (Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu) that co-evolves AI agent skills with a persistent knowledge base in the form of a wiki. Agent skills package specialized knowledge and workflows into reusable resources, and recent approaches automatically discover skills from agent experience. However, insights guiding skill development usually remain scattered across optimization histories, limiting systematic reuse. WikiSkill addresses this by separating raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into a wiki on which subsequent skill updates can build. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill evolution methods and beats skill-free baselines in most model-benchmark settings. The paper also finds skill evolution is complementary to model scaling: larger models benefit more from evolved skills, and smaller models equipped with skills can substantially outperform larger skill-free models. Preprint: arXiv 2608.27454.

Paper Overview

Field: NLP
Authors: Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu
Published: 2026-08-27
arXiv: 2608.27454

Abstract

Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent experience, which enables agents to progressively adapt through interaction. However, the insights that guide skill development typically remain scattered across optimization histories, limiting their systematic reuse across iterations.

Key Points

WikiSkill is a framework that co-evolves agent skills with a persistent knowledge base (a wiki).
It separates raw execution experience, accumulated knowledge, and executable skills.
Experience is continuously consolidated into the wiki, so subsequent skill updates can build on prior knowledge instead of restarting each iteration.
Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill evolution methods.
It also beats skill-free baselines in most model-benchmark settings.
Skill evolution is complementary to model scaling:
Larger models generally gain more from evolved skills.
Smaller models equipped with evolved skills can substantially outperform larger skill-free models.

---

*Collected automatically on 2026-08-30.*