Reliable recovery methods improve AI tool use in changing conditions
Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows
Artificial IntelligenceSoftware Engineering
Summary
Sometimes AI programs need to pause and try again when doing complex tasks, especially if their permission to act changes or the results are unclear. The authors studied how AI agents keep track of permissions, actions, and outcomes to decide if and when they should retry tasks. They tested different ways to check these decisions and found that keeping track of past attempts and external effects helps AI agents recover safely and reliably. The study used both experiments with AI workflow systems and code from a real AI platform to understand the role of permissions and observations in recovery.
What this means in practice
- •For ai platform developers: Make AI workflows more reliable by using permission checks and effect tracking to safely resume operations after interruptions or permission changes.
- •For cloud service operators: Improve monitoring and recovery processes for AI services by integrating ledger-based verification of external actions against declared permissions and contracts.
Authors
Deekshith Marla, Kushagra Bhatnagar
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 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.