| title | Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents |
|---|---|
| authors | Tianpeng Bu, Xin Liu, Qihua Chen, Hao Jiang, Shurui Li, Hongtao Duan, Lu Jiang, Lulu Hu, Bin Yang, Minying Zhang |
| date | 2026-05-28 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.29447 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation and data levels, we introduce GUI-RobustEval and propose Robustness-driven Trajectory Synthesis. GUI-RobustEval contains 1,216 executable test cases that systematically measure error recovery capabilities across a broad and realistic spectrum of error modes. At the data level, RoTS is a scalable synthesis framework that creates 800k high-quality data via a tree-based pipeline that proactively discovers diverse error modes and synthesizes corresponding recovery steps. Our two models, RoTS-7B and RoTS-32B, fine-tuned on our dataset, both demonstrate significant gains on GUI-RobustEval and traditional GUI benchmarks. Notably, RoTS-32B achieves state-of-the-art performance on OSWorld, with a 47.4% success rate and a 33.8% All-Pass@4 score, suggesting that improved long-horizon error recovery ability contributes to both robustness and overall performance. Our code is available at https://github.com/AlibabaResearch/RoTS. |
cite
@misc{bu2026recovering,
title={Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents},
author={Tianpeng Bu and Xin Liu and Qihua Chen and Hao Jiang and Shurui Li and Hongtao Duan and Lu Jiang and Lulu Hu and Bin Yang and Minying Zhang},
year={2026},
eprint={2605.29447},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.29447}
}