Metraipolis › archive › dc_cc223ff2b8e2

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution — arXiv:2608.27454

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27454
License (as archived)
CC0-1.0
Archived
2026-10-17T14:23:54.249Z
SHA-256 of the archived text
4a923c8bb20b7ae8420d541cc975fffd82aa3ac14f2d8cf3a53cf1e88bf20435
Stable URL of this page
https://metraipolis.com/documento/dc_cc223ff2b8e2

How to cite

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution — arXiv:2608.27454 — arXiv (en), https://arxiv.org/abs/2608.27454 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc223ff2b8e2 (Metraipolis archive dc_cc223ff2b8e2, sha256 4a923c8bb20b7ae8420d541cc975fffd82aa3ac14f2d8cf3a53cf1e88bf20435)
BibTeX
@misc{dccc223ff2b8e2,
  title = {WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution — arXiv:2608.27454},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27454},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc223ff2b8e2; sha256 4a923c8bb20b7ae8420d541cc975fffd82aa3ac14f2d8cf3a53cf1e88bf20435},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27454. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.27454 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:53.578Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).