🛰️ Daily AI Frontier
‹ back to 2026-07-21

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

Research LLM Agents

Ranking

Overall 68
Content 80
Popularity 41

Observed public metrics from 1 member.

Merged summary

TL;DR - SEE synthesizes diverse, long-horizon training trajectories for GUI agents by mapping app interfaces into transition graphs and planning paths through them. This reduces dependence on human demonstrations and improves agents’ success and generalization to unseen screens.

  • Builds explicit transition graphs spanning screens and UI elements.
  • Uses graph planning and controlled sampling to compose reproducible, explainable trajectories.
  • Generates 14.8-step trajectories on average while preventing spurious cycles.
  • Fine-tuning on SEE improves performance across multiple real-world apps.

Sources (1)

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

arXiv cs.LG Zhuohang Fan, Beichen Zhang, Yuanfa Li, Changqiao Wu, Wei Liu, Jian Luan, Weigang Zhang 2026-07-20 arXiv:2607.18046
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 2026-08-18 14:38:56.799444 UTC

TL;DR - SEE synthesizes diverse, long-horizon training trajectories for GUI agents by mapping app interfaces into transition graphs and planning paths through them. This reduces dependence on human demonstrations and improves agents’ success and generalization to unseen screens.

  • Builds explicit transition graphs spanning screens and UI elements.
  • Uses graph planning and controlled sampling to compose reproducible, explainable trajectories.
  • Generates 14.8-step trajectories on average while preventing spurious cycles.
  • Fine-tuning on SEE improves performance across multiple real-world apps.
item →