Metraipolis › archive › dc_f9075eaebc2c

A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security — arXiv:2608.29596

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.29596
License (as archived): CC0-1.0
Archived: 2026-10-17T07:41:00.905Z
SHA-256 of the archived text: 71f0b0c7813566a147cc158a6a518c48e9a85f611b2a046602ce7982df40a466
Stable URL of this page: https://metraipolis.com/documento/dc_f9075eaebc2c

How to cite

A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security — arXiv:2608.29596 — arXiv (en), https://arxiv.org/abs/2608.29596 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9075eaebc2c (Metraipolis archive dc_f9075eaebc2c, sha256 71f0b0c7813566a147cc158a6a518c48e9a85f611b2a046602ce7982df40a466)

BibTeX

@misc{dcf9075eaebc2c,
  title = {A Systematic Survey of Agentic Skills: Architecture, Lifecycle, and Security — arXiv:2608.29596},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29596},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9075eaebc2c; sha256 71f0b0c7813566a147cc158a6a518c48e9a85f611b2a046602ce7982df40a466},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29596. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous large language model (LLM) agents increasingly face reliability, context consumption, and execution stability bottlenecks when deployed on complex, long-horizon tasks. While monolithic prompt engineering and stateless tool-calling paradigms struggle to scale, the field is rapidly converging toward \emph{agentic skills}: modular procedural abstractions that externalize execution knowledge into reusable, executable, and portable artifacts. This paper establishes a unified systems foundation and reference architecture for the agentic skills ecosystem. We formalize skills as externalized procedural knowledge bridging high-level cognitive planning with deterministic execution environments, and systematically delineate the architecture across a nine-stage lifecycle: autonomous discovery, authoring and representation formats, memory storage, dynamic retrieval and routing, composition and orchestration, execution and repair, lifelong adaptation, empirical evaluation, and security governance. We further examine marketplace dynamics, public registries, and emerging adversarial threat vectors, alongside runtime verification and defense mechanisms. Finally, we categorize system implementations across software engineering, operating system navigation, embodied robotics, and scientific discovery, while highlighting critical open challenges in continual learning and benchmark realism. This work establishes agentic skills as a foundational paradigm for building scalable, robust, and verifiable autonomous language agents.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.29596 — 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 2026-10-17T07:27:42.005Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).