Metraipolis › archive › dc_1fcbd8ce55f0

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems — arXiv:2608.16381

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16381
License (as archived)
CC0-1.0
Archived
2026-10-18T17:43:04.718Z
SHA-256 of the archived text
c75657091e1e67ae1df7f3055a527f72e7da514be854860b5a2288c0ef5c34f6
Stable URL of this page
https://metraipolis.com/documento/dc_1fcbd8ce55f0

How to cite

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems — arXiv:2608.16381 — arXiv (en), https://arxiv.org/abs/2608.16381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fcbd8ce55f0 (Metraipolis archive dc_1fcbd8ce55f0, sha256 c75657091e1e67ae1df7f3055a527f72e7da514be854860b5a2288c0ef5c34f6)
BibTeX
@misc{dc1fcbd8ce55f0,
  title = {AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems — arXiv:2608.16381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fcbd8ce55f0; sha256 c75657091e1e67ae1df7f3055a527f72e7da514be854860b5a2288c0ef5c34f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages. We introduce a unified execution model that maintains a work item's persistent identity and versioned authoritative state across calls. Each step receives input scoped to a specific state version and new material; a result advances state only after validation and recording. We implement selected paths of this model in AstronOS using Cases, Tasks, and Scenario Packs across central and local execution. We compare five complete strategies for carrying an established software-version update plan into a fresh model session: rereading original materials, replaying full history, deterministic text summary, deterministic JSON, and the AstronOS runtime-mediated handoff. Ten controlled tasks are run under all five strategies with three repetitions, yielding 150 included executions. On the single-stage reference family, strategies perform similarly. In the primary three-stage A-C batch, AstronOS passes the frozen scorer in 14 of 15 executions, compared with 0 of 15 for rereading and 2 of 15 for full-history replay; later non-interleaved summary and JSON batches each pass 0 of 15. AstronOS has lower attempt-accounted model-token cost per passing execution, while requiring more execution-window time per attempt. These results associate the complete AstronOS condition with higher end-to-end pass rates across fresh sessions in this benchmark, at a measurable time cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16381 — 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 2026-10-18T16:29:13.865Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).