AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents

TL;DR

AgentLens is a mobile GUI agent that adaptively switches between visual modalities to optimize human-agent interaction, balancing transparency and multitasking.

Contribution

It introduces a hybrid visual modality system with adaptive communication actions and Virtual Display for background execution in mobile GUI agents.

Findings

85.7% of participants preferred AgentLens.

Achieved high usability score of 1.94 PSSUQ.

High adoption intent score of 6.43 out of 7.

Abstract

Mobile GUI agents can automate smartphone tasks by interacting directly with app interfaces, but how they should communicate with users during execution remains underexplored. Existing systems rely on two extremes: foreground execution, which maximizes transparency but prevents multitasking, and background execution, which supports multitasking but provides little visual awareness. Through iterative formative studies, we found that users prefer a hybrid model with just-in-time visual interaction, but the most effective visualization modality depends on the task. Motivated by this, we present AgentLens, a mobile GUI agent that adaptively uses three visual modalities during human-agent interaction: Full UI, Partial UI, and GenUI. AgentLens extends a standard mobile agent with adaptive communication actions and uses Virtual Display to enable background execution with selective visual overlays. In a controlled study with 21 participants, AgentLens was preferred by 85.7% of participants and achieved the highest usability (1.94 Overall PSSUQ) and adoption-intent (6.43/7).