Image de couverture de livre

OS-Marathon: Benchmarking Computer-Use Agents on Long-Horizon Repetitive Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Jing, Barretto, Daphne, Chen, Yiye, Gydé, Nicholas, Jian, Yanan, He, Yuhang, Vineet, Vibhav
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Physics Knowledge in Frontier Models: A Diagnostic Study of Failure Modes
par: Bagdonaviciute, Ieva, et autres
Publié: (2025)

HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding
par: Azad, Shehreen, et autres
Publié: (2025)

StreamReady: Learning What to Answer and When in Long Streaming Videos
par: Azad, Shehreen, et autres
Publié: (2026)

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes
par: Modi, Rajat, et autres
Publié: (2024)

Navigating Hallucinations for Reasoning of Unintentional Activities
par: Grover, Shresth, et autres
Publié: (2024)

GASP: Gaussian Avatars with Synthetic Priors
par: Saunders, Jack, et autres
Publié: (2024)

Grounding Task Assistance with Multimodal Cues from a Single Demonstration
par: Sarch, Gabriel, et autres
Publié: (2025)

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare
par: Ghosh, Akash, et autres
Publié: (2026)

A Large-Scale Analysis on Contextual Self-Supervised Video Representation Learning
par: Kumar, Akash, et autres
Publié: (2025)

OmViD: Omni-supervised active learning for video action detection
par: Rana, Aayush, et autres
Publié: (2025)

PEEKABOO: Interactive Video Generation via Masked-Diffusion
par: Jain, Yash, et autres
Publié: (2023)

Schema-Guided Scene-Graph Reasoning based on Multi-Agent Large Language Model System
par: Chen, Yiye, et autres
Publié: (2025)

BOSS: Benchmark for Observation Space Shift in Long-Horizon Task
par: Yang, Yue, et autres
Publié: (2025)

Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization
par: Zhang, Yue, et autres
Publié: (2024)

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
par: Grover, Shresth, et autres
Publié: (2025)

Understanding Depth and Height Perception in Large Visual-Language Models
par: Azad, Shehreen, et autres
Publié: (2024)

MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
par: Joshi, Siddharth, et autres
Publié: (2025)

Fara-7B: An Efficient Agentic Model for Computer Use
par: Awadallah, Ahmed, et autres
Publié: (2025)

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames
par: Ravi, Sahithya, et autres
Publié: (2025)

DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
par: Zhao, Brian Nlong, et autres
Publié: (2023)

VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models
par: Chen, Yiye, et autres
Publié: (2026)

OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents
par: Jia, Hongrui, et autres
Publié: (2025)

ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
par: Abaskohi, Amirhossein, et autres
Publié: (2026)

EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
par: Liu, Lulin, et autres
Publié: (2026)

A Skill-augmented Agentic Framework and Benchmark for Multi-Video Understanding
par: Zhang, Yue, et autres
Publié: (2026)

VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
par: Zhang, Shiduo, et autres
Publié: (2024)

Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
par: Song, Xinshuai, et autres
Publié: (2024)

Generalizable Dense Reward for Long-Horizon Robotic Tasks
par: Yong, Silong, et autres
Publié: (2026)

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks
par: Wang, Kaijun, et autres
Publié: (2025)

Future Predictive Success-or-Failure Classification for Long-Horizon Robotic Tasks
par: Sogi, Naoya, et autres
Publié: (2024)

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use
par: Hu, Xueyu, et autres
Publié: (2025)

Robustness Analysis on Foundational Segmentation Models
par: Schiappa, Madeline Chantry, et autres
Publié: (2023)

VSearcher: Long-Horizon Multimodal Search Agent via Reinforcement Learning
par: Zhang, Ruiyang, et autres
Publié: (2026)

AndroTMem: From Interaction Trajectories to Anchored Memory in Long-Horizon GUI Agents
par: Shi, Yibo, et autres
Publié: (2026)

SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
par: Sun, Zeyi, et autres
Publié: (2025)

Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks
par: Kar, Indrajit, et autres
Publié: (2025)

Chameleon: Episodic Memory for Long-Horizon Robotic Manipulation
par: Guo, Xinying, et autres
Publié: (2026)

Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
par: Wang, Jiayu, et autres
Publié: (2024)

RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation
par: Yang, Liudi, et autres
Publié: (2025)

Video-Based Reward Modeling for Computer-Use Agents
par: Song, Linxin, et autres
Publié: (2026)