Bofeee5675/GUI-Net-Benchmark download history
Bofeee5675/GUI-Net-Benchmark is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 29 times (11 in the last 7 days), and 426 times in total. It ranks #281,348 among datasets by monthly downloads.
Introduction In our work TongUI, we benchmarked model performance in various testset. As paper indicated, we proposed our agent as ReAct, so it outputs thought and actions. However, the offline benchmarks we used does not contain thought in the dataset, so we managed to generate thought f