arXiv:2608. 05587v1 Announce Type: new Abstract: Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution.
By Linqiang Guo (Peter), Wei Liu (Peter), Li Gu (Peter), Yang Wang (Peter), Tse-Hsun (Peter), Chen
Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal reasoning after each action, which is costly and poorly matched to the structured nature of GUI state transitions.
arXiv:2509.23263v3 Announce Type: replace
Abstract: Long-horizon GUI automation remains challenging due to error accumulation over extended interaction sequences. Process Reward Models (PRMs) provide...
By Tao Xiong, Xavier Hu, Yurun Chen, Yuhang Liu, Changqiao Wu, Pengzhi Gao, Wei Liu, Jian Luan, Shengyu Zhang
The paper introduces Evidence-First Reflection (EFR), a two-stage reflector for desktop GUI agents that separates visual difference extraction from outcome verification. EFR uses Set-of-Marks annotations to locate action sites and candidate changed regions, filters action-relevant changes, and then makes a final judgment based on cleaned evidence. Experiments on OSWorld-Verified and WindowsAgentArena show that EFR improves reflector accuracy by 7.11% and increases end-to-end task success by roughly 5–6%.
By Yijie Ma, Chaoyue Niu, Fan Wu, Guihai Chen
arXiv:2606. 31410v1 Announce Type: new Abstract: Graphical user interface (GUI) agents build on vision-language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, text entry, and navigation.
By Wanxia Cao, Chengzhen Duan, Pei Fu, Pengzhi Gao, Niu Lian, Fazhan Liu, Hui Liu, Heng Qu, Qinzhuo Wu, Zhehao Yu, Tongbo Chen, Shiqi Cui, Anan Du, Shukai Jia, Yuanfa Li, Yike Liu, Wenchao Lu, Haoyuan Sun, Jiatong Sun, Cheng Tan, Yajie Wang, Changqiao Wu, Tao Xiong, Jiahui Yang, Yuxuan Yuan, Ruoceng Zhang, Shaojie Zhang, Jian Zhu, Jian Luan, Cong Zou
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
By Xing Han L\`u, Dheeraj Vattikonda, Sina Hajimiri, Fatemeh Pesaran Zadeh, Parishad BehnamGhader, Ghazwa Darwiche, Amirhossein Kazemnejad, Christopher Pal, Alexandre Drouin, Siva Reddy