ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “Computer Use Agents”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.MAcs.CLcs.LGRecentJun 1, 2026

Multi-Agent Computer Use

Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

View →
cs.HCcs.CLEmpiricalRecentOct 30, 2026

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

Haoqing Wang, Xiaoyi Zhang, Sicheng Fan, Zhexin Zhang +4 more

The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.

View →
cs.CRcs.ETcs.HCMar 30, 2026

"What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents

Zifan Peng, Mingchen Li

The paper addresses the lack of user understanding regarding the actions and residual effects of advanced computer-use agents by proposing AgentTrace, a traceability framework for visualizing agent be…

View →
cs.AIcs.CLcs.HCEmpiricalRecentJun 21, 2026

MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop

Yikun Fu, Bowen Fu, Zhenyu Wu, Shuang Cheng +9 more

The paper presents MacAgentBench, a comprehensive macOS agent benchmark for evaluating computer use agents.

View →
cs.CRMay 14, 2026

Toward Securing AI Agents Like Operating Systems

Lukas Pirch, Micha Horlboge, Patrick Großmann, Syeda Mahnur Asif +3 more

This paper analyzes the security of LLM-based autonomous agents by drawing parallels to operating system security, finding that while some vulnerabilities are inherent, many can be mitigated using est…

View →
cs.CRcs.AIcs.CLMay 14, 2026

Web Agents Should Adopt the Plan-Then-Execute Paradigm

Julien Piet, Annabella Chow, Yiwei Hou, Muxi Lyu +4 more

The paper argues that web agents should abandon the reactive ReAct paradigm in favor of a plan-then-execute approach, which requires developing typed, task-level APIs to properly structure web interac…

View →
cs.OScs.AIcs.CRRecentJun 2, 2026

Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents

Yingqi Zhang

Agent libOS introduces a library-OS-inspired runtime substrate that treats LLM agents as schedulable processes, providing explicit capability control and robust auditing for long-running, stateful age…

View →
cs.OScs.AIcs.CREmpiricalRecentJun 2, 2026

Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents

Yingqi Zhang

This paper presents Agent libOS, a library-OS-inspired runtime substrate for long-running language model agents.

View →
cs.CRMay 2, 2026

FP-Agent: Fingerprinting AI Browsing Agents

Ethan Wang, Zubair Shafiq, Yash Vekaria

The paper introduces FP-Agent, a classifier that demonstrates that while browser fingerprints are poor discriminators for AI browsing agents, behavioral fingerprints (like typing and scrolling pattern…

View →
cs.PLcs.AIcs.CRMay 13, 2026

Language-Based Agent Control

Timothy Zhou, Loris D'Antoni, Nadia Polikarpova

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

View →
cs.CRcs.AIcs.PLMar 21, 2026

AC4A: Access Control for Agents

Reshabh K Sharma, Dan Grossman

The paper introduces AC4A, an access control framework that allows users to precisely limit the capabilities of LLM agents, ensuring they only access the specific APIs or parts of web pages necessary…

View →
cs.CRcs.AIMay 20, 2026

PocketAgents: A Manifest-Driven Library of Autonomous Defense Agents

Sidnei Barbieri, Ágney Lopes Roth Ferraz, Lourenço Alves Pereira Júnior

PocketAgents introduces a manifest-driven framework for autonomous defense agents, enabling measurable and attributable LLM-driven security responses by strictly controlling agent actions and telemetr…

View →
cs.AIcs.DBRecentMay 27, 2026

A Query Engine for the Agents

Kenny Daniel

The paper introduces Hyperparam, a set of lightweight JavaScript libraries designed to enable direct, model-aware querying of unstructured data (like agent traces) within client-side AI applications.

View →
cs.CRcs.OSApr 20, 2026

AgenTEE: Confidential LLM Agent Execution on Edge Devices

Sina Abdollahi, Mohammad M Maheri, Javad Forough, Amir Al Sadi +4 more

AgenTEE is a system that enables the secure, confidential execution of complex LLM agent pipelines directly on edge devices by using isolated confidential virtual machines.

View →
cs.CRcs.AIRecentJun 1, 2026

Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems

Ankur Sharma, Deep Shah

The paper proposes the concept of an Agent Operating System (AOS) to provide a necessary systems foundation for managing the unique, non-deterministic, and goal-directed execution characteristics of m…

View →
cs.CRcs.AIRecentJun 1, 2026

Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems

Ankur Sharma, Deep Shah

The paper proposes the concept of an Agent Operating System (AOS) to provide a rigorous, controllable, and accountable systems foundation for running complex, probabilistic, and goal-directed AI agent…

View →
cs.CRMay 6, 2026

WAAA! Web Adversaries Against Agentic Browsers

Sohom Datta, Alex Nahapetyan, William Enck, Alexandros Kapravelos

This paper proposes the first web-focused threat model for agentic browsers, demonstrating that traditional web social engineering attacks can be amplified into dangerous, reproducible threats when ex…

View →
cs.SEcs.AIEmpiricalRecentJun 10, 2026

Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production

Marc Alier Forment, Juanan Pereira, Francisco José García-Peñalvo, María José Casañ Guerrero

A methodology for building custom AI agents

View →
cs.CRcs.AIMay 18, 2026

Agent Security is a Systems Problem

Mihai Christodorescu, Earlence Fernandes, Ashish Hooda, Somesh Jha +10 more

The paper argues that agent security must be treated as a systems problem, requiring the enforcement of security invariants at the system level rather than solely relying on improving the underlying A…

View →