Copertina

On the Reliability of Computer Use Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gonzalez-Pumariega, Gonzalo, Agashe, Saaket, Yang, Jiachen, Li, Ang, Wang, Xin Eric
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
di: Agashe, Saaket, et al.
Pubblicazione: (2025)

Agent S: An Open Agentic Framework that Uses Computers Like a Human
di: Agashe, Saaket, et al.
Pubblicazione: (2024)

Scaling Agents for Computer Use
di: Gonzalez-Pumariega, Gonzalo, et al.
Pubblicazione: (2025)

Self-Resource Allocation in Multi-Agent LLM Systems
di: Amayuelas, Alfonso, et al.
Pubblicazione: (2025)

EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
di: Juneja, Gurusha, et al.
Pubblicazione: (2026)

Robotouille: An Asynchronous Planning Benchmark for LLM Agents
di: Gonzalez-Pumariega, Gonzalo, et al.
Pubblicazione: (2025)

Stateful Reasoning via Insight Replay
di: Lei, Bin, et al.
Pubblicazione: (2026)

Query-Efficient Planning with Language Models
di: Gonzalez-Pumariega, Gonzalo, et al.
Pubblicazione: (2024)

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
di: Agashe, Saaket, et al.
Pubblicazione: (2023)

Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare
di: Ekpo, Promise Osaine, et al.
Pubblicazione: (2025)

MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
di: Yan, Yunhe, et al.
Pubblicazione: (2025)

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
di: Yang, Jingyi, et al.
Pubblicazione: (2025)

OSExpert: Computer-Use Agents Learning Professional Skills via Exploration
di: Liu, Jiateng, et al.
Pubblicazione: (2026)

Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
di: Guo, Ruocheng, et al.
Pubblicazione: (2026)

Human-Guided Harm Recovery for Computer Use Agents
di: Li, Christy, et al.
Pubblicazione: (2026)

PRO-CUA: Process-Reward Optimization for Computer Use Agents
di: He, Yifei, et al.
Pubblicazione: (2026)

Multi-Turn Code Generation Through Single-Step Rewards
di: Jain, Arnav Kumar, et al.
Pubblicazione: (2025)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
di: Sun, Jingwei, et al.
Pubblicazione: (2026)

A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis
di: Liu, Jiachen, et al.
Pubblicazione: (2025)

Context Bootstrapped Reinforcement Learning
di: Agashe, Saaket, et al.
Pubblicazione: (2026)

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
di: Feng, Yunhao, et al.
Pubblicazione: (2026)

Identification of Probabilities of Causation: from Recursive to Closed-Form Bounds
di: Shu, Xin, et al.
Pubblicazione: (2025)

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
di: Foerster, Hanna, et al.
Pubblicazione: (2026)

OpenCUA: Open Foundations for Computer-Use Agents
di: Wang, Xinyuan, et al.
Pubblicazione: (2025)

The Art of Building Verifiers for Computer Use Agents
di: Rosset, Corby, et al.
Pubblicazione: (2026)

IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
di: Chen, Rongqian, et al.
Pubblicazione: (2026)

The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
di: Wang, Xinrun, et al.
Pubblicazione: (2026)

Grounding Computer Use Agents on Human Demonstrations
di: Feizi, Aarash, et al.
Pubblicazione: (2025)

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
di: Wang, Dayu, et al.
Pubblicazione: (2025)

C-World: A Computer Use Agent Environment Creator
di: Xi, Ziqiao, et al.
Pubblicazione: (2026)

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
di: Lai, Hanyu, et al.
Pubblicazione: (2025)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
di: Wei, Jinbiao, et al.
Pubblicazione: (2026)

Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents
di: Tang, Sizhe, et al.
Pubblicazione: (2026)

S-Agents: Self-organizing Agents in Open-ended Environments
di: Chen, Jiaqi, et al.
Pubblicazione: (2024)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
di: Hu, Xuhao, et al.
Pubblicazione: (2026)

P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference
di: Peng, Xin, et al.
Pubblicazione: (2026)

DPO Learning with LLMs-Judge Signal for Computer Use Agents
di: Luo, Man, et al.
Pubblicazione: (2025)

SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations
di: Xie, Eric, et al.
Pubblicazione: (2025)

DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation
di: Gu, Tianjun, et al.
Pubblicazione: (2025)

Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent
di: Cheng, Yuhao, et al.
Pubblicazione: (2025)