arXiv cs.CL
· Papers
Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation
arXiv:2608.02694v1 Announce Type: new Abstract: Long-horizon video editing agents receive final-product feedback only after many interdependent decisions. Yet editing quality is subjective, admits multiple valid solutions, and is not meaningfully calibrated across heterogeneous requests, making a global scalar objectiv