🛰️ Daily AI Frontier
‹ back to 2026-08-03

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

Research LLM Agents

Ranking

Overall 69
Content 80
Popularity 43

Observed public metrics from 1 member.

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

Merged summary

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.

Sources (1)

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

arXiv cs.AI Hang Yan, Zhangxuan GU, Beitong Zhou, Jiaxuan Chen, Runze Li, Yusong Hu, Shuheng Shen, Changhua Meng 2026-07-31 arXiv:2607.29320
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-08 14:19:06.065250 UTC

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.
item →