Year: 2026
Type: preprint
Abstract: This is an earlier single-author preprint. A later revision with additional authors has been submitted to IEEE Transactions on Reliability for consideration. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Supplementary aggregate results are available separately at https://doi.org/10.5281/zenodo.24369921. When a language-model agent's tool call is interrupted, the action may already have changed an external system without confirmation. Retrying risks duplication; assuming success may conceal an action that never occurred. We study these failure modes in a controlled agent runtime combining authorization, an action ledger, target-side idempotency, reconciliation, and evidence sealing. We inject ten single-host fault classes and compare four configurations and three ablations using a target-side oracle separate from the runtime ledger. On each of Windows and Linux, 7,513 trials used 96 captured model responses from 24 constructed cases. In 200 known original crash and replay pairs, the full configuration recorded 0/200 repeated effects versus 117/200 for each simpler baseline. A ledger-related ablation had 170/170 orphaned effects versus 0/170 and 200/300 recovery successes versus 300/300 for the full configuration. Disabling reconciliation left 100/100 known post-effect crash outcomes ambiguous despite no observed duplicates. A separate supplement designed after the initial results and reusing the same inputs found a similar pattern under response loss or delay. The full runtime had about one-seventh of fail-open throughput, while injected evidence-write faults left 75/100 trials per platform unresolved. These findings distinguish duplicate suppression from recovery and identify their measured reliability and performance tradeoffs within the tested benchmark.
Source: arXiv (Cornell University)
Author: Xu, Song
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7233992680
