Paper Detail

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

Tianpeng Bu, Xin Liu, Qihua Chen, Hao Jiang, Shurui Li, Hongtao Duan, Lu Jiang, Lulu Hu, Bin Yang, Minying Zhang

huggingface Score 16.2

Published 2026-05-28 · First seen 2026-06-01

Research Track B · General AI

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@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},
  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 tha},
  url = {https://huggingface.co/papers/2605.29447},
  keywords = {GUI agents, error recovery, GUI-RobustEval, Robustness-driven Trajectory Synthesis, OSWorld, All-Pass@4, code available, huggingface daily},
  eprint = {2605.29447},
  archiveprefix = {arXiv},
}

Metadata

{}