Papers by Honghui Sheng
DAC-Bench: A Decision-Aware Benchmark for Compositional Mobile GUI Tasks (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on short, linear workflows and step-level accuracy, highlighting performance degradations. |
| Approach: | They propose a decision-aware benchmark with compositional tasks comprising 830 episodes and 11,345 action steps across 35 applications on Android and iOS. |
| Outcome: | The proposed benchmarks show performance degradation and branch correctness issues in 7 different GUI agents. |