Understanding Tool-Mediated Interaction Failures in Agentic GUI Software: An Empirical Study
Source
arxiv.org
Author
Yuchen Shao (East China Normal University, Shanghai Innovation Institute), Wenjing Liu (East China Normal University), Yuheng Huang (University of Tokyo), Mengqian Xu (East China Normal University Shanghai Innovation Institute), Ziqun Bao (East China Normal University), Long Yang (East China Normal University Shanghai Innovation Institute), Lei Ma (University of Tokyo University of Alberta), Ting Su (East China Normal University), Chengcheng Wan (East China Normal University Shanghai Innovation Institute)
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleThe Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent BehaviorXiangzhe Xu, Hamidreza Saghir, Qianhui Wu, Marc-Alexandre C\^ot\'e, Tong Wang, Kiran Lakkaraju, Kexin Pei, Xiangyu Zhang
articleToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling AgentsYiShan Zheng, Yuan Wu, Yi Chang
articleWhen Passing Tests Hides Vulnerabilities: An Empirical Study of Silent Failures in Agentic SystemsWenji Bai, Muhammad Waseem, Zeeshan Rasheed, Jaakko Peltonen, Pekka Abrahamsson