LATIDIA · Investigación

Permiso para reintentar: un estudio de autorización y recuperación en flujos de trabajo de agentes de IA

arXiv:2610.31916v1 Tipo de anuncio: nuevo Resumen: Un agente duradero puede reanudar una acción consecuente mientras su autoridad cambia y el resultado externo de la acción sigue siendo incierto. Estudiamos la fiabilidad del tiempo de ejecución de a

La noticia

arXiv:2610.31916v1 Announce Type: new Abstract: 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