Back to Home
arXiv AI··Papers & Tech

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

中文摘要

该研究探讨使用工具的 AI 智能体在执行任务时的可靠性,重点研究如何将授权与恢复流程从语言模型行为中分离出来。

English Summary

This study examines the reliability of tool-using AI agents, focusing on authorization and recovery processes by isolating execution-time decisions from language model behavior.

Original Excerpt

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 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 Arya.ai, exercises e…