中文
相关论文

相关论文: A Comprehensive Survey of Agents for Computer Use:…

200 篇论文

Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…

信息检索 · 计算机科学 2026-05-27 Yingli Zhou , Wang Shu , Yaodong Su , Wenchuan Du , Yixiang Fang , Xuemin Lin

The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic…

多智能体系统 · 计算机科学 2025-10-21 Xinfeng Li , Dong Huang , Jie Li , Hongyi Cai , Zhenhong Zhou , Wei Dong , XiaoFeng Wang , Yang Liu

Imagine a world where AI can handle your work while you sleep - organizing your research materials, drafting a report, or creating a presentation you need for tomorrow. However, while current digital agents can perform simple tasks, they…

人工智能 · 计算机科学 2024-12-24 Yanheng He , Jiahe Jin , Shijie Xia , Jiadi Su , Runze Fan , Haoyang Zou , Xiangkun Hu , Pengfei Liu

Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we present OmegaUse, a…

Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they…

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating…

人工智能 · 计算机科学 2026-05-01 Jinchao Li , Yunxin Li , Chenrui Zhao , Zhenran Xu , Baotian Hu , Min Zhang

Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this…

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…

Today's AI agents are built on large language models (LLMs) equipped with tools to access and modify external environments, such as corporate file systems, API-accessible platforms and websites. AI agents offer the promise of automating…

计算机与社会 · 计算机科学 2026-03-26 Merlin Stein

An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…

密码学与安全 · 计算机科学 2025-11-26 Zehang Deng , Yongjian Guo , Changzhou Han , Wanlun Ma , Junwu Xiong , Sheng Wen , Yang Xiang

Large language model (LLM)-based computer use agents execute user commands by interacting with available UI elements, but little is known about how users want to interact with these agents or what design factors matter for their user…

人机交互 · 计算机科学 2026-02-10 Ruijia Cheng , Jenny T. Liang , Eldon Schoop , Jeffrey Nichols

As Large Language Models (LLMs) evolve from code generators into collaborative partners for software engineers, our methods for evaluation are lagging. Current benchmarks, focused on code correctness, fail to capture the nuanced,…

软件工程 · 计算机科学 2026-01-01 Tao Dong , Harini Sampath , Ja Young Lee , Sherry Y. Shi , Andrew Macvean

Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically address. We show that a 1MB replay script that blindly executes a recorded action sequence…

Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and…

多智能体系统 · 计算机科学 2026-01-30 Alok Kamatar , J. Gregory Pauloski , Yadu Babuji , Ryan Chard , Mansi Sakarvadia , Daniel Babnigg , Kyle Chard , Ian Foster

Repurposing large vision-language models (LVLMs) as computer use agents (CUAs) has led to substantial breakthroughs, primarily driven by human-labeled data. However, these models often struggle with novel and specialized software,…

人工智能 · 计算机科学 2025-08-13 Zeyi Sun , Ziyu Liu , Yuhang Zang , Yuhang Cao , Xiaoyi Dong , Tong Wu , Dahua Lin , Jiaqi Wang

Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…

密码学与安全 · 计算机科学 2026-01-12 Sahaya Jestus Lazer , Kshitiz Aryal , Maanak Gupta , Elisa Bertino

Graphical User Interface (GUI) agents adopt an end-to-end paradigm that maps a screenshot to an action sequence, thereby automating repetitive tasks in virtual environments. However, existing GUI agents are evaluated almost exclusively on…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Chunyi Li , Longfei Li , Zicheng Zhang , Xiaohong Liu , Min Tang , Weisi Lin , Guangtao Zhai

Automating GUI tasks remains challenging due to reliance on textual representations, platform-specific action spaces, and limited reasoning capabilities. We introduce Aguvis, a unified vision-based framework for autonomous GUI agents that…

计算与语言 · 计算机科学 2025-05-06 Yiheng Xu , Zekun Wang , Junli Wang , Dunjie Lu , Tianbao Xie , Amrita Saha , Doyen Sahoo , Tao Yu , Caiming Xiong

AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…

Agentic AI represents a significant shift in how intelligence is applied within organizations, moving beyond AI-assisted tools toward autonomous systems capable of reasoning, decision-making, and coordinated action across workflows. As…