中文
相关论文

相关论文: CutVerse: A Compositional GUI Agents Benchmark for…

200 篇论文

The rapid development of diffusion models has significantly advanced AI-generated content (AIGC), particularly in Text-to-Image (T2I) and Text-to-Video (T2V) generation. Text-based video editing, leveraging these generative capabilities,…

计算机视觉与模式识别 · 计算机科学 2025-01-22 Yupeng Chen , Penglin Chen , Xiaoyu Zhang , Yixian Huang , Qian Xie

Graphical User Interface (GUI) action grounding is a critical step in GUI automation that maps language instructions to actionable elements on GUI screens. Most recent works of GUI action grounding leverage large GUI datasets to fine-tune…

计算与语言 · 计算机科学 2025-01-28 Yue Fan , Handong Zhao , Ruiyi Zhang , Yu Shen , Xin Eric Wang , Gang Wu

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a…

计算与语言 · 计算机科学 2026-01-09 Ziyun Zhang , Zezhou Wang , Xiaoyi Zhang , Zongyu Guo , Jiahao Li , Bin Li , Yan Lu

End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data, yet collecting human demonstrations is expensive and existing synthetic pipelines often suffer from limited task diversity or noisy,…

人工智能 · 计算机科学 2026-04-14 Jinbiao Wei , Yilun Zhao , Kangqi Ni , Arman Cohan

Generative models have substantially expanded video generation capabilities, yet practical thought-to-video creation remains a multi-stage, multi-modal, and decision-intensive process. However, existing tools either hide intermediate…

多媒体 · 计算机科学 2026-02-10 Zhuoyun Zheng , Yu Dong , Gaorong Liang , Guan Li , Guihua Shan , Shiyu Cheng , Dong Tian , Jianlong Zhou , Jie Liang

Graphical user interface (GUI) grounding, the process of mapping human instructions to GUI actions, serves as a fundamental basis to autonomous GUI agents. While existing grounding models achieve promising performance to simulate the mouse…

人机交互 · 计算机科学 2026-01-13 Zeyi Liao , Yadong Lu , Boyu Gou , Huan Sun , Ahmed Awadallah

Computer Use Agents (CUAs) are designed to autonomously operate digital interfaces, yet they often fail to reliably determine whether a given task has been completed. We present an autonomous evaluation and feedback framework that uses…

人工智能 · 计算机科学 2025-11-26 Marta Sumyk , Oleksandr Kosovan

Reproducing cognitive development, group interaction, and long-term evolution in virtual classrooms remains a core challenge for educational AI, as real classrooms integrate open-ended cognition, dynamic social interaction, affective…

计算机视觉与模式识别 · 计算机科学 2025-10-08 Yiping Ma , Shiyu Hu , Buyuan Zhu , Yipei Wang , Yaxuan Kang , Shiqing Liu , Kang Hao Cheong

Block-based programming environments such as Scratch play a central role in low-code education, yet evaluating the capabilities of AI agents to construct programs through Graphical User Interfaces (GUIs) remains underexplored. We introduce…

人工智能 · 计算机科学 2026-02-12 Xingyi Zhang , Yulei Ye , Kaifeng Huang , Wenhao Li , Xiangfeng Wang

Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Xuan Ju , Tianyu Wang , Yuqian Zhou , He Zhang , Qing Liu , Nanxuan Zhao , Zhifei Zhang , Yijun Li , Yuanhao Cai , Shaoteng Liu , Daniil Pakhomov , Zhe Lin , Soo Ye Kim , Qiang Xu

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents…

信息检索 · 计算机科学 2026-04-10 Maria Movin , Claudia Hauff , Aron Henriksson , Panagiotis Papapetrou

Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction, evolving from rule-based automation scripts to sophisticated AI-driven systems capable of understanding and executing complex…

Computer-use agents face a fundamental limitation. They rely exclusively on primitive GUI actions (click, type, scroll), creating brittle execution chains prone to cascading failures. While API-driven agents harness rich capabilities…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Yuhao Yang , Zhen Yang , Zi-Yi Dou , Anh Nguyen , Keen You , Omar Attia , Andrew Szot , Michael Feng , Ram Ramrakhya , Alexander Toshev , Chao Huang , Yinfei Yang , Zhe Gan

Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs) but doing so remains a costly and time-intensive process. Prior work has used computer…

计算与语言 · 计算机科学 2026-04-30 Alice Gao , Weixi Tong , Rishab Vempati , Katharina Reinecke , R. Benjamin Shapiro , Tianyi Zhang , Jason Wu

Visually-guided image editing, where edits are conditioned on both visual cues and textual prompts, has emerged as a powerful paradigm for fine-grained, controllable content generation. Although recent generative models have shown…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Sara Ghazanfari , Wei-An Lin , Haitong Tian , Ersin Yumer

Current benchmarks for graphical user interface (GUI) agents predominantly rely on static screenshots. However, real-world smartphone interaction routinely requires agents to process transient audio cues and temporal video dynamics that are…

人机交互 · 计算机科学 2026-05-20 Felix Henry , Xiaochen Lin , Jiangyou Zhu , Yangfan , Bingqian Zhang , Min Chen , Shiyu Huang

Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text…

计算机视觉与模式识别 · 计算机科学 2025-07-28 Yusu Qian , Jiasen Lu , Tsu-Jui Fu , Xinze Wang , Chen Chen , Yinfei Yang , Wenze Hu , Zhe Gan

As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To…

Utilizing Graphic User Interface (GUI) for human-computer interaction is essential for accessing a wide range of digital tools. Recent advancements in Vision Language Models (VLMs) highlight the compelling potential to develop versatile…

Generating a game is not the same as making one that can be played. Despite advances in code generation, existing approaches treat game generation as one-shot translation from prompt to artifact, leaving interaction-level failures…

软件工程 · 计算机科学 2026-05-28 Yixu Huang , Bo Li , Na Li , Zhe Wang , Kaijie Chen , Haonan Ge , Qingyi Si , Yuanzhe Shen , Ruihan Yang , Guangjing Wang , Hongcheng Guo