Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon}, the number of trajectory tokens retained for training, and show that it is a key design axis for reliability and cost. Reliability improv...
Cuong Dang, Just Anh Hoang, Ruo-Xi Jia
· 0 citations