Preprint
Aug 2026
Reflection with Action-Induced Visual Differences for Desktop GUI Agents
Evidence-First Reflection (EFR), a two-stage reflector that explicitly decouples action-induced visual differences extraction from outcome verification, makes reflection better grounded in screen transitions, while reducing both visual search complexity and reasoning burden.
Yijie Ma, Chaoyue Niu, Fan Wu et al.
· 0 citations