On the Reliability of Computer Use Agents
For researchers developing computer-use agents, this work highlights the overlooked problem of execution unreliability and provides actionable insights for improving robustness.
The paper investigates why computer-use agents that succeed once often fail on repeated executions of the same task, identifying stochasticity, task ambiguity, and behavioral variability as key sources of unreliability. Experiments on OSWorld show that reliability depends on task specification and agent behavior variation.
Computer-use agents have rapidly improved on real-world tasks such as web navigation, desktop automation, and software interaction, in some cases surpassing human performance. Yet even when the task and model are unchanged, an agent that succeeds once may fail on a repeated execution of the same task. This raises a fundamental question: if an agent can succeed at a task once, what prevents it from doing so reliably? In this work, we study the sources of unreliability in computer-use agents through three factors: stochasticity during execution, ambiguity in task specification, and variability in agent behavior. We analyze these factors on OSWorld using repeated executions of the same task together with paired statistical tests that capture task-level changes across settings. Our analysis shows that reliability depends on both how tasks are specified and how agent behavior varies across executions. These findings suggest the need to evaluate agents under repeated execution, to allow agents to resolve task ambiguity through interaction, and to favor strategies that remain stable across runs.