English
Related papers

Related papers: UFO2: The Desktop AgentOS

200 papers

Vision-and-Language Scene navigation is a fundamental capability for embodied human-AI collaboration, requiring agents to follow natural language instructions to execute coherent action sequences in complex environments. Existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Kaiming Jin , Yuefan Wu , Shengqiong Wu , Bobo Li , Shuicheng Yan , Tat-Seng Chua

Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…

Cryptography and Security · Computer Science 2026-01-15 Haochen Gong , Chenxiao Li , Rui Chang , Wenbo Shen

Modern Unmanned Aerial Vehicles equipped with state of the art artificial intelligence (AI) technologies are opening to a wide plethora of novel and interesting applications. While this field received a strong impact from the recent AI…

Computer Vision and Pattern Recognition · Computer Science 2020-04-15 Enkhtogtokh Togootogtokh , Christian Micheloni , Gian Luca Foresti , Niki Martinel

This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question…

Artificial Intelligence · Computer Science 2025-09-03 Jiabo Ye , Xi Zhang , Haiyang Xu , Haowei Liu , Junyang Wang , Zhaoqing Zhu , Ziwei Zheng , Feiyu Gao , Junjie Cao , Zhengxi Lu , Jitong Liao , Qi Zheng , Fei Huang , Jingren Zhou , Ming Yan

As large language models (LLM)-driven agents transition from isolated task solvers to persistent digital entities, the emergence of the Agentic Web, an ecosystem where heterogeneous agents autonomously interact and co-evolve, marks a…

The emergence of agentic AI, powered by Large Language Models (LLMs), marks a paradigm shift from reactive generative systems to proactive, goal-oriented autonomous agents capable of sophisticated planning, memory, and tool use. This…

Artificial Intelligence · Computer Science 2025-09-05 Yineng Yan , Xidong Wang , Jin Seng Cheng , Ran Hu , Wentao Guan , Nahid Farahmand , Hengte Lin , Yue Li

Graphical User Interface (GUI) Agents, powered by multimodal large language models (MLLMs), have shown great potential for task automation on computing devices such as computers and mobile phones. However, existing agents face challenges in…

Artificial Intelligence · Computer Science 2025-01-09 Yuhang Liu , Pengxiang Li , Zishu Wei , Congkai Xie , Xueyu Hu , Xinchen Xu , Shengyu Zhang , Xiaotian Han , Hongxia Yang , Fei Wu

Currently, agent-based simulation frameworks force the user to choose between simulations involving a large number of agents (at the expense of limited agent reasoning capability) or simulations including agents with increased reasoning…

Simulated user agents are increasingly used in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoning, but the unstructured nature of this output often obscures…

Human-Computer Interaction · Computer Science 2026-01-23 Steffen Holter , Eunyee Koh , Mustafa Doga Dogan , Gromit Yeuk-Yin Chan

This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of building agentic systems suitable for enterprise environments. By…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-10 Sami Marreed , Alon Oved , Avi Yaeli , Segev Shlomov , Ido Levy , Offer Akrabi , Aviad Sela , Asaf Adi , Nir Mashkif

Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use…

Computer-use agents hold the promise of assisting in a wide range of digital economic activities. However, current research has largely focused on short-horizon tasks over a limited set of software with limited economic value, such as basic…

Machine Learning · Computer Science 2026-04-08 Pranjal Aggarwal , Graham Neubig , Sean Welleck

We introduce QiboAgent, a reference implementation designed to serve as a practitioner's guideline for developing specialized coding assistants in Quantum Computing middleware. Addressing the limitations in scientific software development…

Quantum Physics · Physics 2026-03-17 Lorenzo Esposito , Andrea Papaluca , Stefano Carrazza

GUI task automation streamlines repetitive tasks, but existing LLM or VLM-based planner-executor agents suffer from brittle generalization, high latency, and limited long-horizon coherence. Their reliance on single-shot reasoning or static…

Artificial Intelligence · Computer Science 2025-09-29 Seoyoung Lee , Seonbin Yoon , Seongbeen Lee , Hyesoo Kim , Joo Yong Sim

UI task automation enables efficient task execution by simulating human interactions with graphical user interfaces (GUIs), without modifying the existing application code. However, its broader adoption is constrained by the need for…

Human-Computer Interaction · Computer Science 2025-03-19 Tian Huang , Chun Yu , Weinan Shi , Zijian Peng , David Yang , Weiqi Sun , Yuanchun Shi

Recent advances in operating system (OS) agents have enabled vision-language models (VLMs) to directly control a user's computer. Unlike conventional VLMs that passively output text, OS agents autonomously perform computer-based tasks in…

Cryptography and Security · Computer Science 2026-01-28 Lukas Aichberger , Alasdair Paren , Guohao Li , Philip Torr , Yarin Gal , Adel Bibi

Large language models (LLMs) have moved far beyond their initial form as simple chatbots, now carrying out complex reasoning, planning, writing, coding, and research tasks. These skills overlap significantly with those that human scientists…

Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…

Cryptography and Security · Computer Science 2025-09-25 Aaron Xuxiang Tian , Ruofan Zhang , Janet Tang , Ji Wang , Tianyu Shi , Jiaxin Wen

We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on tasks like web interaction, tool use, or software automation in generic settings,…

Artificial Intelligence · Computer Science 2026-04-02 Zhe Yang , Shulin Tian , Kairui Hu , Shuai Liu , Hoang-Nhat Nguyen , Yichi Zhang , Zujin Guo , Mengying Yu , Zinan Zhang , Jingkang Yang , Chen Change Loy , Ziwei Liu

With the growing reliance on digital devices equipped with graphical user interfaces (GUIs), such as computers and smartphones, the need for effective automation tools has become increasingly important. While multimodal large language…

Human-Computer Interaction · Computer Science 2024-10-18 Jakub Hoscilowicz , Bartosz Maj , Bartosz Kozakiewicz , Oleksii Tymoshchuk , Artur Janicki