Introduces VG-GUIBench benchmark and TASKER keyframe extraction algorithm that improves performance on VideoQA and video-guided agentic tasks.
VideoAgentTrek: Computer use pretraining from unlabeled videos, 2025
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
CUA-Gym generates 32,112 verified RLVR tuples across 110 mock environments, enabling trained models to reach 62.1% and 72.6% on OSWorld-Verified while transferring to WebArena.
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.
PhoneWorld is a pipeline that converts real mobile trajectories into scalable controllable environments, yielding large gains on four benchmarks when used to supplement training data.
citing papers explorer
-
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
CUA-Gym generates 32,112 verified RLVR tuples across 110 mock environments, enabling trained models to reach 62.1% and 72.6% on OSWorld-Verified while transferring to WebArena.
-
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
OSWorld 2.0 is a benchmark of 108 realistic long-horizon computer-use tasks where current agents achieve only 20.6% binary completion, struggling with state inference and constraint tracking.