Diverse GUI Interaction Logs Enhance Generalization in GUI Agents Across Unseen Domains

This report synthesises findings from 11 peer-reviewed papers addressing the following research question: What is the impact of including diverse GUI interaction logs in the fine-tuning dataset on the macro-averaged success rate of GUI agents across unseen domains in the AppSight benchmark. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: What is the impact of including diverse GUI interaction logs in the fine-tuning dataset on the macro-averaged success rate of GUI agents across unseen domains in the AppSight benchmark?

Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.