Year: 2026
Type: conference-paper
Abstract: Mobile GUI agents powered by LMMs can perceive screens and follow instructions, yet existing benchmarks largely target short, linear workflows and step-level accuracy, offering limited insight into long-horizon planning and decision-making under branching structures.We present DAC-Bench, a decisionaware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS.Tasks are organized into Sequential, Conjunctive, Conditional, and Hierarchical structures, reflecting real-world multi-step and branching interaction patterns.To complement standard step-level evaluation, we introduce weighted longest common subsequence to capture length-sensitive progress and decision accuracy for branch correctness.Evaluations across 7 diverse agents show substantial performance degradation compared to prior benchmarks, with success rates dropping below 5% on 6-8 step tasks and branch accuracy averaging 38%, highlighting challenges in conditional decision-making.By exposing these failure modes, DAC-Bench provides a challenging and diagnostic benchmark for advancing decision-aware mobile GUI agents.Our
Institution: Zhejiang University
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G1101031052, G2567805129, G5672621438
OpenAlex ID: W7166800086