Metraipolis › archive › dc_3a67b8640722

Stateful Governance for Concurrent Agentic Systems — arXiv:2608.02764

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02764
License (as archived)
CC0-1.0
Archived
2026-10-31T12:14:33.526Z
SHA-256 of the archived text
f021621be9055b46b03d51a3404430b2986faf5ddb981ab74f4090c5d4ded08f
Stable URL of this page
https://metraipolis.com/documento/dc_3a67b8640722

How to cite

Stateful Governance for Concurrent Agentic Systems — arXiv:2608.02764 — arXiv (en), https://arxiv.org/abs/2608.02764 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a67b8640722 (Metraipolis archive dc_3a67b8640722, sha256 f021621be9055b46b03d51a3404430b2986faf5ddb981ab74f4090c5d4ded08f)
BibTeX
@misc{dc3a67b8640722,
  title = {Stateful Governance for Concurrent Agentic Systems — arXiv:2608.02764},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02764},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a67b8640722; sha256 f021621be9055b46b03d51a3404430b2986faf5ddb981ab74f4090c5d4ded08f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02764. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents are moving from advisory interfaces into systems that execute consequential operations: issuing refunds, reserving scarce inventory, provisioning cloud resources, and initiating financial transfers. These workflows require governance over effects, not only over model outputs. Existing safeguards often decide whether an action is allowed from the information available when the action is requested. For stateful policies, that request-time view may be incomplete: budgets, inventory, approval status, and risk signals can change before the effect occurs, making an earlier authorization or approval stale. This paper studies stateful governance for concurrent agentic systems. We identify stale authorization as the core failure mode and define policy-state serializability, a correctness condition requiring committed effects to be explainable as authorized against the policy state immediately before they occur. We present MasuGate, a runtime architecture that keeps policies as reviewable programs while coordinating the state and effects needed to preserve their decisions. In experiments with a PostgreSQL-backed prototype of MasuGate, the system prevents stale authorizations missed by baselines that pass policy state as ordinary request context, preserves delayed approvals while unrelated work proceeds, keeps policy evolution mostly in policy text rather than trusted provider code, and avoids policy violations in a scripted, LLM-free procurement workflow where agent-governance baselines produce stale authorizations over shared budgets and inventory. More broadly, MasuGate suggests a path for integrating stateful governance boundaries into agent frameworks and provider-backed domains where agents act on shared resources.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2608.02764 — 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 2026-10-31T12:05:27.210Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).