Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution

Source

arXiv

arxiv.org/abs/2608.27454v1

Read the source

Source

  • Source name: arXiv
  • Source kind: paper
  • Authors / organization: Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng, Andrew Tomkins, Da-Cheng Juan, Tu Vu
  • Venue: arXiv: cs.AI
  • Published: 2026-08-27
  • Collected: 2026-08-29
  • URL: http://arxiv.org/abs/2608.27454v1
  • PDF: https://arxiv.org/pdf/2608.27454v1
  • DOI: UNKNOWN
  • Registry group: academic_apis_and_preprints
  • Evidence role: canonical_academic_index
  • Language: en
  • Country / region: UNKNOWN

Plain-Language Brief

WikiSkill is a framework that helps AI agents evolve their skills by creating a persistent knowledge base (wiki) to store and consolidate their experiences. This framework outperforms other skill-evolution methods, improves over no-skill baselines in most model-benchmark settings, and complements model scaling. Evolved skills also transfer effectively across models and model families.

What the Document Says

  • Agent skills are resources that extend AI agent capabilities and can be developed automatically from agent experience.
  • WikiSkill is a framework that co-evolves agent skills with a persistent knowledge base (wiki).
  • Raw execution experience, accumulated knowledge, and executable skills are separated in WikiSkill.
  • The wiki continuously consolidates experience for subsequent skill updates to build on.
  • WikiSkill outperforms state-of-the-art skill-evolution methods across diverse benchmarks and models.
  • Improvement over no-skill baselines is noted in most model-benchmark settings.
  • Larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them.
  • Evolved skills transfer effectively across models and model families.
  • Skills evolved by other models can outperform self-evolved skills.
  • Persistent knowledge accumulation in the wiki is critical for effective skill evolution.

Key Concepts Mentioned

  • AI agents
  • skills
  • skill evolution
  • persistent knowledge base (wiki)
  • execution experience
  • accumulated knowledge

Claims Made by the Document

  • WikiSkill outperforms state-of-the-art skill-evolution methods.
  • Improvement over no-skill baselines is noted in most model-benchmark settings.
  • Larger models generally benefit more from evolved skills.
  • Smaller models with skills can outperform substantially larger models without them.
  • Evolved skills transfer effectively across models and model families.
  • Skills evolved by other models can outperform self-evolved skills.
  • Persistent knowledge accumulation in the wiki is critical for effective skill evolution.

Evidence Used

  • Consistently outperforms state-of-the-art skill-evolution methods across diverse benchmarks and models.
  • Improvement over no-skill baselines in most model-benchmark settings.
  • Larger models generally benefit more from evolved skills.
  • Smaller models with skills can outperform substantially larger models without them.
  • Evolved skills transfer effectively across models and model families.
  • Skills evolved by other models can outperform self-evolved skills.
  • Persistent knowledge accumulation in the wiki is critical for effective skill evolution.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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. We introduce WikiSkill, a framework that co-evolves agent skills with a persistent knowledge base (wiki). At a high level, WikiSkill separates raw execution experience, accumulated knowledge, and executable skills, while continuously consolidating experience into the wiki, which subsequent skill updates can build on. Across diverse benchmarks and models, WikiSkill consistently outperforms state-of-the-art skill-evolution methods and improves over no-skill baselines in most model-benchmark settings. We find that skill evolution complements model scaling: larger models generally benefit more from evolved skills, while smaller models with skills can outperform substantially larger models without them. We also find that evolved skills transfer effectively across models and model families, and skills evolved by other models can outperform self-evolved skills. Finally, our ablation studies confirm that persistent knowledge accumulation in the wiki is critical for effective skill evolution. These results demonstrate the benefits of systematically accumulating and refining agent experience for developing reusable and transferable skills.