Morae: Proactively Pausing UI Agents for User Choices

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Peng, Yi-Hao, Li, Dingzeyu, Bigham, Jeffrey P., Pavel, Amy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912558931247104
author Peng, Yi-Hao
Li, Dingzeyu
Bigham, Jeffrey P.
Pavel, Amy
author_facet Peng, Yi-Hao
Li, Dingzeyu
Bigham, Jeffrey P.
Pavel, Amy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21456
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Morae: Proactively Pausing UI Agents for User Choices
Peng, Yi-Hao
Li, Dingzeyu
Bigham, Jeffrey P.
Pavel, Amy
Human-Computer Interaction
Computation and Language
Computer Vision and Pattern Recognition
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.
title Morae: Proactively Pausing UI Agents for User Choices
topic Human-Computer Interaction
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.21456