works on
anticipatory planning 1benchmark evaluation 1computer-use agents 1error analysis 1gui automation 1latency reduction 1multimodal models 1policy trees 1reliability 1task scoring 1

From the 2 of 14 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

How Benchmarks Mis-Score Computer-Use Agents

Zihan Dong, Zhiyuan Ma, Zekun Wang +5

The paper examines how current benchmarks for computer-use agents often give inaccurate scores due to issues in task design, trajectory observation, scoring, and reporting, and pro…