MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation

TL;DR - MAGA is a distillation method that fuses multiple domain-specific GUI agents (mobile, web, desktop) into one cross-environment policy by weighting the training signal toward structured action tokens. It matters because it avoids the action corruption of weight merging while beating standard on-policy distillation on multi-platform GUI control.

• Frames the problem as consolidating specialized GUI experts: weight merging can corrupt executable actions when experts disagree, and on-policy distillation treats all response tokens equally despite actions being the only agent–environment interface.
• Re-allocates the distillation signal based on generated-action correctness — suppressing unnecessary or invalid signals and concentrating learning on erroneous actions.
• Adds a training-only hint that improves the supervision from domain-specific teachers without altering the student's input.
• Reported across two model scales: highest mean success rate, +2.0% over the strongest baseline at 8B, and roughly parity with the individual teachers on average.