Knowing When to \texttt{STOP}, \texttt{RECOVER}, and \texttt{SEARCH} \\ A Modular Framework for GUI Automation

Qijun Han, Haoqin Tu, Zijun Wang, Haoyue Dai, Yiyang Zhou, Nancy Lau, Alvaro A. Cardenas, Yuhui Xu, Ran Xu, Caiming Xiong, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie

Keywords: Computer-use Agent, Multi-modal Agent, Agentic Systems

Abstract:

Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops, where agents cycle through the same failing actions without recovery.
We present GUI-Pro-Agent, a modular GUI agentic framework built around three integrated components that guide the system on when to Stop, Recover, and Search.
First, a mandatory Completeness Verifier enforces UI-observable success criteria and verification at every finish step—with an agent-level verifier that cross-examines completion claims with decision rules, rejecting those lacking direct visual evidence.
Second, a mandatory Loop Breaker provides multi-tier filtering: switching interaction mode after repeated failures, forcing strategy changes after persistent screen-state recurrence, and binding reflection signals to strategy shifts.
Third, an on-demand Search Agent searches online for unfamiliar workflows by directly querying a capable LLM with search ability, returning results as plain text.
We additionally integrate a Coding Agent for code-intensive actions and a Grounding Agent for precise action grounding, both invoked on demand when required.
We evaluate GUI-Pro-Agent across five top-tier backbones, including Opus 4.5, 4.6 and Gemini 3.1 Pro, on two benchmarks with Linux and Windows tasks, achieving top performance on both (77.5% on OSWorld and 61.0% on WindowsAgentArena). Notably, three of the five backbones surpass human performance (i.e., 72.4%) on OSWorld in a single pass.
In particular, GUI-Pro-Agent with Sonnet 4.6 at only 15 action steps already surpasses the best published 50-step system.
Ablation studies show that all three proposed components consistently improve a strong backbone (e.g., Sonnet 4.6), while a weaker backbone (e.g., Gemini 3 Flash) benefits more from these tools when the step budget is sufficient.
Further analysis also shows that the Loop Breaker nearly halves wasted steps for loop-prone models.

Track: Regular Paper (9 pages)

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 87