English
Related papers

Related papers: UI-CUBE: Enterprise-Grade Computer Use Agent Bench…

200 papers

Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of realistic user simulation frameworks hinders their development. Existing approaches model apps as flat…

Artificial Intelligence · Computer Science 2026-04-02 Deepak Nathani , Cheng Zhang , Chang Huan , Jiaming Shan , Yinfei Yang , Alkesh Patel , Zhe Gan , William Yang Wang , Michael Saxon , Xin Eric Wang

We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…

Artificial Intelligence · Computer Science 2024-10-11 Saaket Agashe , Jiuzhou Han , Shuyu Gan , Jiachen Yang , Ang Li , Xin Eric Wang

Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps.…

Artificial Intelligence · Computer Science 2026-05-29 Rongqian Chen , Yu Li , Zeyu Fang , Sizhe Tang , Weidong Cao , Tian Lan

Modern AI systems lack a way to express and enforce requirements. Pre-training produces intelligence, and post-training optimizes preferences, but neither guarantees that models reliably satisfy explicit, context-dependent constraints. This…

Software Engineering · Computer Science 2025-12-18 David Ball

Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with…

Artificial Intelligence · Computer Science 2026-05-13 Xuhao Hu , Xi Zhang , Haiyang Xu , Kyle Qiao , Jingyi Yang , Xuanjing Huang , Jing Shao , Ming Yan , Jieping Ye

Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and…

Artificial Intelligence · Computer Science 2026-04-22 Daniel Shepard , Robin Salimans

User eXperience (UX) is becoming increasingly important for success of software products. Yet, many companies still face various challenges in their work with UX. Part of these challenges relate to inadequate knowledge and awareness of UX…

Software Engineering · Computer Science 2016-06-30 Pariya Kashfi , Robert Feldt , Agneta Nilsson , Richard Berntsson Svensson

Performance models that statically predict the steady-state throughput of basic blocks on particular microarchitectures, such as IACA, Ithemal, llvm-mca, OSACA, or CQA, can guide optimizing compilers and aid manual software optimization.…

Performance · Computer Science 2022-05-23 Andreas Abel , Jan Reineke

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

Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Kevin Qinghong Lin , Linjie Li , Difei Gao , Qinchen WU , Mingyi Yan , Zhengyuan Yang , Lijuan Wang , Mike Zheng Shou

IMPORTANCE: Modern ultrasound systems are universal diagnostic tools capable of imaging the entire body. However, current AI solutions remain fragmented into single-task tools. This critical gap between hardware versatility and software…

Effectively scaling GUI automation is essential for computer-use agents (CUAs); however, existing work primarily focuses on scaling GUI grounding rather than the more crucial GUI planning, which requires more sophisticated data collection.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Deyang Jiang , Jing Huang , Xuanle Zhao , Lei Chen , Liming Zheng , Fanfan Liu , Haibo Qiu , Peng Shi , Zhixiong Zeng

We describe WebSuite, the first diagnostic benchmark for generalist web agents, designed to systematically evaluate why agents fail. Advances in AI have led to the rise of numerous web agents that autonomously operate a browser to complete…

Software Engineering · Computer Science 2024-06-05 Eric Li , Jim Waldo

Given the significant advances in Large Vision Language Models (LVLMs) in reasoning and visual understanding, mobile agents are rapidly emerging to meet users' automation needs. However, existing evaluation benchmarks are disconnected from…

Computation and Language · Computer Science 2025-08-18 Zeyu Huang , Juyuan Wang , Longfeng Chen , Boyi Xiao , Leng Cai , Yawen Zeng , Jin Xu

A growing number of critical workflow applications leverage a streamlined edge-hub-cloud architecture, which diverges from the conventional edge computing paradigm. An edge device, in collaboration with a hub device and a cloud server,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-23 Andreas Kouloumpris , Georgios L. Stavrinides , Maria K. Michael , Theocharis Theocharides

Basic-block throughput models such as uiCA, IACA, GRANITE, Ithemal, llvm-mca, OSACA, or CQA guide optimizing compilers and help performance engineers identify and eliminate bottlenecks. For this purpose, basic-block throughput models should…

Performance · Computer Science 2023-10-23 Andreas Abel , Shrey Sharma , Jan Reineke

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

Existing benchmarks do not test language agents on their interaction with human users or ability to follow domain-specific rules, both of which are vital for deploying them in real world applications. We propose $\tau$-bench, a benchmark…

Artificial Intelligence · Computer Science 2024-06-19 Shunyu Yao , Noah Shinn , Pedram Razavi , Karthik Narasimhan

Software robots have long been used in Robotic Process Automation (RPA) to automate mundane and repetitive computer tasks. With the advent of Large Language Models (LLMs) and their advanced reasoning capabilities, these agents are now able…

Artificial Intelligence · Computer Science 2024-12-30 Junhee Cho , Jihoon Kim , Daseul Bae , Jinho Choo , Youngjune Gwon , Yeong-Dae Kwon

Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g.,…

Cryptography and Security · Computer Science 2026-04-09 Guruprasad Viswanathan Ramesh , Asmit Nayak , Basieem Siddique , Kassem Fawaz