works on
agent evaluation 1asynchronous runtime 1benchmark 1benchmarking 1computer-use agents 1cross-platform evaluation 1large language models 1reward modeling 1software infrastructure 1vision-language models 1

From the 2 of 11 linked papers with an AI index.

collaborators
Showing cs.MAShow all

1 paper · 1 filter

cs.MA2026

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent

Bowen Yang, Kaiming Jin, Zhenyu Wu +12

While Vision-Language Models (VLMs) have significantly advanced Computer-Using Agents (CUAs), current frameworks struggle with robustness in long-horizon workflows and generalizati…