Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents

TL;DR

This paper explores how augmenting usability heuristics can enhance the robustness and reliability of computer-use agents across evolving interfaces, combining interface design improvements with agent capabilities.

Contribution

It introduces augmented heuristics based on Nielsen's principles, evaluated through controlled environments and human studies, to improve agent task success and efficiency.

Findings

Augmented heuristics improve task completion rates.

Design augmentations modestly increase efficiency.

Human studies show no usability regressions.

Abstract

Recent advances have enabled general computer-use agents that interpret screens and execute grounded actions from human instructions, yet they still struggle to generalize to unseen and evolving interfaces. While improving agent capability remains important, agent compatible interface design offers a complementary path by aligning interaction semantics with agent prior knowledge. In this paper, we revisit Nielsen 10 usability heuristics through the lens of computer-use agents, identifying which principles naturally transfer, where implicit design assumptions create agent specific failures, and how safe additive augmentations can improve robustness without harming human usability. To evaluate these ideas, we introduce UI-Verse, a suite of controlled environments built around functionally similar interfaces with different applied heuristics. Experiments show that our augmented heuristics consistently improve task completion and modestly improve efficiency, with combined heuristics yielding further gains. Human studies further show that these designs preserve the original interaction workflow without observable usability regressions. Overall, our findings highlight interface design as a practical complementary avenue for improving the reliability and generalization of computer use agents.