Morae: Proactively Pausing UI Agents for User Choices
This addresses the issue of reduced user agency for blind and low-vision users when using automated UI agents, representing an incremental improvement by adding mixed-initiative interaction.
The paper tackles the problem of UI agents reducing user agency by making decisions without involving users, and introduces Morae, a UI agent that proactively pauses at decision points to allow user choices, which in a study with BLV participants helped complete more tasks and better match preferences compared to baseline agents.
User interface (UI) agents promise to make inaccessible or complex UIs easier to access for blind and low-vision (BLV) users. However, current UI agents typically perform tasks end-to-end without involving users in critical choices or making them aware of important contextual information, thus reducing user agency. For example, in our field study, a BLV participant asked to buy the cheapest available sparkling water, and the agent automatically chose one from several equally priced options, without mentioning alternative products with different flavors or better ratings. To address this problem, we introduce Morae, a UI agent that automatically identifies decision points during task execution and pauses so that users can make choices. Morae uses large multimodal models to interpret user queries alongside UI code and screenshots, and prompt users for clarification when there is a choice to be made. In a study over real-world web tasks with BLV participants, Morae helped users complete more tasks and select options that better matched their preferences, as compared to baseline agents, including OpenAI Operator. More broadly, this work exemplifies a mixed-initiative approach in which users benefit from the automation of UI agents while being able to express their preferences.