Metraipolis › archive › dc_731cb9be981f

Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems — arXiv:2611.07652

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07652
License (as archived)
CC0-1.0
Archived
2026-11-06T14:41:41.618Z
SHA-256 of the archived text
3ec0fd55f2ca211ce781c709ad7be7d4d5859829958795ce539eb16252992803
Stable URL of this page
https://metraipolis.com/documento/dc_731cb9be981f

How to cite

Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems — arXiv:2611.07652 — arXiv (en), https://arxiv.org/abs/2611.07652 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_731cb9be981f (Metraipolis archive dc_731cb9be981f, sha256 3ec0fd55f2ca211ce781c709ad7be7d4d5859829958795ce539eb16252992803)
BibTeX
@misc{dc731cb9be981f,
  title = {Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems — arXiv:2611.07652},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07652},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_731cb9be981f; sha256 3ec0fd55f2ca211ce781c709ad7be7d4d5859829958795ce539eb16252992803},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07652. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt engineering. In practice, this burns massive context windows, inflates API bills, and produces brittle agents that fail unpredictably in production. In this work, we present Skillware, an open architectural framework and capability registry that formally separates what an agent wants to do from how that task is executed. Instead of prompting models with loose text instructions or markdown files baptized as 'skills', Skillware equips them with modular, versioned software capability bundles. Much like skill hotkeys in video games that execute deterministically under fixed world rules, each bundle combines a typed JSON input contract, deterministic Python code, task directives, bundled datasets, and automated unit tests. In-process adapters translate these capabilities into native tool declarations for any model, from frontier cloud APIs to local open-weight runtimes with zero network latency. Evaluating 23 frontier and open-weight models across 368 benchmark conditions, we show that small local models (3B to 8B parameters) equipped with Skillware consistently outperform unequipped frontier models on complex multi-step workflows. They cut token usage by up to 84.8%, slash inference costs by up to 97.3%, and eliminate parameter errors entirely. True agent reliability does not come from larger models or longer prompts, but from equipping logical systems with verified, deterministic software. Finally, we articulate the trajectory of capability bundles across an invariant continuum of information processing systems: from digital logical systems today, to IoT, drones, and embodied robotics tomorrow, establishing a foundation for auditable, real-time capability execution.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.07652 — 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 2026-11-06T14:18:42.643Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).