SEE: Structure-aware Exploring & Exploiting for Long-horizon GUI Agent Trajectory Synthesis

The paper introduces SEE, a two-stage framework for generating long-horizon GUI agent trajectories. First, an exploration stage builds an explicit UI transition graph over screens and elements. Second, a graph-based synthesis stage composes diverse multi-step trajectories through planning and controlled sampling, preventing spurious cycles and enabling long-horizon composition. Across real-world apps, SEE produces trajectories averaging 14.8 steps and improves agent task success and generalization to unseen screens.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• llms
• agents
• fine-tuning
• multimodal