WebKD: Minimal Editing of Failed Web Agent Episodes in Student’s Style
arXiv reports that frontier web agents that rely on closed models incur high inference and computational costs . arXiv reports that smaller open models are a potential alternative but require training supervision from a human or teacher model . arXiv reports that the paper introduces WebKD, in which a teacher edits a student’s failed episode by locating the first mistake and rewriting the reasoning traces, states, and actions from that point onward . arXiv reports that WebKD aims to edit minimally, with the teacher writing each correction in the student’s own style, and that the teacher’s corrections can be more surprising to the student than the student’s own text .
Why it matters. Because the teacher’s corrections can be more surprising, they may draw the student’s attention to errors, while writing in the student’s style keeps feedback familiar .