A self-generating graph benchmark produces 36k GUI agent tasks with controllable complexity and ten capability scores, and fine-tuning on its trajectories gives small gains on AndroidControl and OmniAct.
Video-of-thought: Step-by-step video reasoning from perception to cognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
A self-generating graph benchmark produces 36k GUI agent tasks with controllable complexity and ten capability scores, and fine-tuning on its trajectories gives small gains on AndroidControl and OmniAct.