OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and system state. However, native GUI/code coordination cannot be obtained by prompt-level tool composition. In our preliminary experiments, naively addi...
Bowen Yang, K. Jin, Zichen Ding et al.
· 0 citations