Metraipolis › archive › dc_8bac61e4cd79

SKILL.state: Scalable Long-Horizon Agent Skills — arXiv:2608.26263

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26263
License (as archived)
CC0-1.0
Archived
2026-10-17T13:16:40.617Z
SHA-256 of the archived text
9d1bb9230fabfa27ed83c255f31e268bb63d614024a3a6b9eb3b4d1f062bceeb
Stable URL of this page
https://metraipolis.com/documento/dc_8bac61e4cd79

How to cite

SKILL.state: Scalable Long-Horizon Agent Skills — arXiv:2608.26263 — arXiv (en), https://arxiv.org/abs/2608.26263 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bac61e4cd79 (Metraipolis archive dc_8bac61e4cd79, sha256 9d1bb9230fabfa27ed83c255f31e268bb63d614024a3a6b9eb3b4d1f062bceeb)
BibTeX
@misc{dc8bac61e4cd79,
  title = {SKILL.state: Scalable Long-Horizon Agent Skills — arXiv:2608.26263},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26263},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bac61e4cd79; sha256 9d1bb9230fabfa27ed83c255f31e268bb63d614024a3a6b9eb3b4d1f062bceeb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26263. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning traces to an ever-growing conversation history, causing latency degradation and context-poisoning failures over long horizons. We present SKILL. state, a runtime architecture that replaces append-only conversational history with an explicit, mutable execution state. At each execution step, the model receives only the immutable skill specification, the current structured execution state, and the latest observation. Intermediate reasoning is discarded immediately after producing a validated state update, preventing prompt growth with execution history. Across diverse datasets, models, and execution environments, SKILL. state improves task accuracy while substantially reducing cumulative token consumption. Our results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.26263 — 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 2026-10-17T13:16:16.999Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).