כתבה
arXiv cs.LG ·
GUI-HARVEST: סוכנים עצמאיים ל-GUI
GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
GUI-HARVEST הוא כלי לאופטימיזציה של סוכנים עצמאיים ל-GUI. הוא משפר את הביצועים של מודלים כמו Qwen3-VL-32B-Instruct ו-GPT-5.
תקציר מקורי באנגליתarXiv:2610.00948v1 Announce Type: new Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled. Compared with harness optimization for non-GUI agents, automatically optimizing this harness poses three coupled challenges: reconciling model intent with observed visual effects, diagnosing failures under variable execution outcomes, and identifying recurrent failure patterns across tasks and translating them into reusable runtime changes. We introduce GUI-HARVEST, an automatic harness optimizer that enables self-improving GUI agents with frozen backbone models. First, to ground diagnosis in observed action effects, it aligns model outputs and executed actions with before-
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית