Metraipolis › archive › dc_c839d2bebf67

Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows — arXiv:2610.31916

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31916
License (as archived)
CC0-1.0
Archived
2026-10-26T19:47:35.068Z
SHA-256 of the archived text
cbdaee72c5ff6db62f7b4d870b074d6d656cd1d6f1c2e42d64fff7c6256a104d
Stable URL of this page
https://metraipolis.com/documento/dc_c839d2bebf67

How to cite

Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows — arXiv:2610.31916 — arXiv (en), https://arxiv.org/abs/2610.31916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c839d2bebf67 (Metraipolis archive dc_c839d2bebf67, sha256 cbdaee72c5ff6db62f7b4d870b074d6d656cd1d6f1c2e42d64fff7c6256a104d)
BibTeX
@misc{dcc839d2bebf67,
  title = {Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows — arXiv:2610.31916},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31916},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c839d2bebf67; sha256 cbdaee72c5ff6db62f7b4d870b074d6d656cd1d6f1c2e42d64fff7c6256a104d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of tool-using AI agents, isolating recovery decisions from language-model behavior. Checkpoint state, permission to dispatch, evidence of an external effect and permission to reconcile are distinct obligations. We present a finite conformance study that checks these obligations through histories scored against a provider effect ledger hidden from the recovering application. A prospectively frozen campaign executes 336 histories on native LangGraph and Temporal hosts, crossing 14 schedules, three provider contracts and four matched application policies. All 168 paired host cells have identical checked outcomes. Per host, retained-ledger reconciliation passes all 42 histories: 21 checked completions, 15 denials and six unknown outcomes with reservations retained. Cached retry, revalidation before retry and stable-key retry pass 30, 36 and 31 histories respectively. A separate 16-case component study of InfinityOS, an enterprise AI platform developed by this http URL , exercises exported authority, worker, recovery and settlement code over repository fakes. The results isolate the roles of current authority, provider contracts and retained observations in recovery, with safety, completion and unresolved obligations reported separately for the declared application profile.

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/2610.31916 — 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 2026-10-26T19:45:33.269Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).