Imagen de Portada

OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agents

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Abhyankar, Reyna, Qi, Qi, Zhang, Yiying
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Machine Learning Operating Systems
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents
por: Wang, Yuan, et al.
Publicado: (2025)

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents
por: Huang, Yutong, et al.
Publicado: (2026)

Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning
por: He, Zijian, et al.
Publicado: (2025)

EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
por: Feng, Shaoting, et al.
Publicado: (2025)

AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving
por: Feng, Shaoting, et al.
Publicado: (2025)

Semantic Scheduling for LLM Inference
por: Hua, Wenyue, et al.
Publicado: (2025)

Preparation Meets Opportunity: Enhancing Data Preprocessing for ML Training With Seneca
por: Desai, Omkar, et al.
Publicado: (2025)

An Integrated Artificial Intelligence Operating System for Advanced Low-Altitude Aviation Applications
por: Tan, Minzhe, et al.
Publicado: (2024)

Neuralink: Fast LLM Inference on Smartphones with Neuron Co-Activation Linking
por: Wang, Tuowei, et al.
Publicado: (2024)

Enhancing Battery Storage Energy Arbitrage with Deep Reinforcement Learning and Time-Series Forecasting
por: Sage, Manuel, et al.
Publicado: (2024)

LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS
por: Mei, Kai, et al.
Publicado: (2025)

Sawtooth Wavefront Reordering: Enhanced CuTile FlashAttention on NVIDIA GB10
por: Zhu, Yifan, et al.
Publicado: (2026)

Secure and Efficient Access Control for Computer-Use Agents via Context Space
por: Gong, Haochen, et al.
Publicado: (2025)

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
por: Gu, Yile, et al.
Publicado: (2025)

Hardware-Assisted Virtualization of Neural Processing Units for Cloud Platforms
por: Xue, Yuqi, et al.
Publicado: (2024)

AgentCgroup: Understanding and Controlling OS Resources of AI Agents
por: Zheng, Yusheng, et al.
Publicado: (2026)

Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contexts
por: Tushir, Bhagyashri, et al.
Publicado: (2024)

Learning Semantics, Not Addresses: Runtime Neural Prefetching for Far Memory
por: Huang, Yutong, et al.
Publicado: (2025)

Skim: Speculative Execution for Fast and Efficient Web Agents
por: Wong, Mike, et al.
Publicado: (2026)

Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
por: Zheng, Yusheng, et al.
Publicado: (2025)

Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
por: Wu, Tianyuan, et al.
Publicado: (2026)

DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
por: Dong, Yunpeng, et al.
Publicado: (2026)

Energy-Efficient Computation with DVFS using Deep Reinforcement Learning for Multi-Task Systems in Edge Computing
por: Li, Xinyi, et al.
Publicado: (2024)

Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores
por: Wu, Chenpeng, et al.
Publicado: (2025)

Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
por: Kamahori, Keisuke, et al.
Publicado: (2024)

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

AIOS: LLM Agent Operating System
por: Mei, Kai, et al.
Publicado: (2024)

Integrating Artificial Intelligence into Operating Systems: A Survey on Techniques, Applications, and Future Directions
por: Zhang, Yifan, et al.
Publicado: (2024)

CaMDN: Enhancing Cache Efficiency for Multi-tenant DNNs on Integrated NPUs
por: Cai, Tianhao, et al.
Publicado: (2025)

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
por: Dang, Pucheng, et al.
Publicado: (2025)

ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation
por: Wang, Shihao, et al.
Publicado: (2026)

Cerebrum (AIOS SDK): A Platform for Agent Development, Deployment, Distribution, and Discovery
por: Rama, Balaji, et al.
Publicado: (2025)

An AI Agent Execution Environment to Safeguard User Data
por: Stanley, Robert, et al.
Publicado: (2026)

Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs
por: Wang, Yifan, et al.
Publicado: (2025)

Composable OS Kernel Architectures for Autonomous Intelligence
por: Singh, Rajpreet, et al.
Publicado: (2025)

FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference
por: Du, Hongchao, et al.
Publicado: (2025)

NaSh: Guardrails for an LLM-Powered Natural Language Shell
por: Gyawali, Bimal Raj, et al.
Publicado: (2025)

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
por: Agarwal, Shubham, et al.
Publicado: (2025)

UFO2: The Desktop AgentOS
por: Zhang, Chaoyun, et al.
Publicado: (2025)

LithOS: An Operating System for Efficient Machine Learning on GPUs
por: Coppock, Patrick H., et al.
Publicado: (2025)