# BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism Source: [BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:57:17.113Z Authors: Qinzhuo Wu, Pengzhi Gao, Wei Liu, Jian Luan Published: 2025-05-27T03:09:06.000Z ## Abstract Graphical User Interface (GUI) agents have gained substantial attention due to their impressive capabilities to complete tasks through multiple interactions within GUI environments. However, existing agents primarily focus on enhancing the accuracy of individual actions and often lack effective mechanisms for detecting and recovering from errors. To address these shortcomings, we propose the BacktrackAgent, a robust framework that incorporates a backtracking mechanism to improve task completion efficiency. BacktrackAgent includes verifier, judger, and reflector components as modules for error detection and recovery, while also applying judgment rewards to further enhance the agent's performance. Additionally, we develop a training dataset specifically designed for the backtracking mechanism, which considers the outcome pages after action executions. Experimental results show that BacktrackAgent has achieved performance improvements in both task success rate and step accuracy on Mobile3M and Auto-UI benchmarks. Our data and code will be released upon acceptance. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Action Success Prediction on AndroidWorld (smallest held-out split)](): Action Success Prediction; AndroidWorld (smallest held-out split); Precision: 75.6. ## Original sources and implementation [Original paper]() [PDF]()