HATS: Hardness-Aware Trajectory Synthesis for GUI Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914387917275136 |
|---|---|
| author | Shao, Rui Gao, Ruize Xie, Bin Li, Yixing Zhou, Kaiwen Wang, Shuai Guan, Weili Chen, Gongwei |
| author_facet | Shao, Rui Gao, Ruize Xie, Bin Li, Yixing Zhou, Kaiwen Wang, Shuai Guan, Weili Chen, Gongwei |
| contents | Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training. Yet existing trajectory synthesis pipelines often yield agents that fail to generalize beyond simple interactions. We identify this limitation as stemming from the neglect of semantically ambiguous actions, whose meanings are context-dependent, sequentially dependent, or visually ambiguous. Such actions are crucial for real-world robustness but are under-represented and poorly processed in current datasets, leading to semantic misalignment between task instructions and execution. To address these issues, we propose HATS, a Hardness-Aware Trajectory Synthesis framework designed to mitigate the impact of semantic ambiguity. We define hardness as the degree of semantic ambiguity associated with an action and develop two complementary modules: (1) hardness-driven exploration, which guides data collection toward ambiguous yet informative interactions, and (2) alignment-guided refinement, which iteratively validates and repairs instruction-execution alignment. The two modules operate in a closed loop: exploration supplies refinement with challenging trajectories, while refinement feedback updates the hardness signal to guide future exploration. Extensive experiments show that agents trained with HATS consistently outperform state-of-the-art baselines across benchmark GUI environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12138 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HATS: Hardness-Aware Trajectory Synthesis for GUI Agents Shao, Rui Gao, Ruize Xie, Bin Li, Yixing Zhou, Kaiwen Wang, Shuai Guan, Weili Chen, Gongwei Computer Vision and Pattern Recognition Graphical user interface (GUI) agents powered by large vision-language models (VLMs) have shown remarkable potential in automating digital tasks, highlighting the need for high-quality trajectory data to support effective agent training. Yet existing trajectory synthesis pipelines often yield agents that fail to generalize beyond simple interactions. We identify this limitation as stemming from the neglect of semantically ambiguous actions, whose meanings are context-dependent, sequentially dependent, or visually ambiguous. Such actions are crucial for real-world robustness but are under-represented and poorly processed in current datasets, leading to semantic misalignment between task instructions and execution. To address these issues, we propose HATS, a Hardness-Aware Trajectory Synthesis framework designed to mitigate the impact of semantic ambiguity. We define hardness as the degree of semantic ambiguity associated with an action and develop two complementary modules: (1) hardness-driven exploration, which guides data collection toward ambiguous yet informative interactions, and (2) alignment-guided refinement, which iteratively validates and repairs instruction-execution alignment. The two modules operate in a closed loop: exploration supplies refinement with challenging trajectories, while refinement feedback updates the hardness signal to guide future exploration. Extensive experiments show that agents trained with HATS consistently outperform state-of-the-art baselines across benchmark GUI environments. |
| title | HATS: Hardness-Aware Trajectory Synthesis for GUI Agents |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.12138 |