On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
arXiv preprint arXiv:2510.19488 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Introduces VG-GUIBench benchmark and TASKER keyframe extraction algorithm that improves performance on VideoQA and video-guided agentic tasks.
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.
PhoneBuddy combines real-app and mock-app RL after shared SFT, raising real-phone task success from 36.67% to 45.33% and AndroidWorld from 60.3% to 83.2%.
Demo2Tutorial distills human screen recordings into hierarchical image-text tutorials that outperform human-authored ones on a documentation-derived benchmark and improve downstream human task speed and GUI-agent planning.
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
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
-
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
Introduces VG-GUIBench benchmark and TASKER keyframe extraction algorithm that improves performance on VideoQA and video-guided agentic tasks.
-
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.
-
PhoneBuddy: Training Open Models for Agentic Phone Use
PhoneBuddy combines real-app and mock-app RL after shared SFT, raising real-phone task success from 36.67% to 45.33% and AndroidWorld from 60.3% to 83.2%.
-
Demo2Tutorial: From Human Experience to Multimodal Software Tutorials
Demo2Tutorial distills human screen recordings into hierarchical image-text tutorials that outperform human-authored ones on a documentation-derived benchmark and improve downstream human task speed and GUI-agent planning.
-
PhoneWorld: Scaling Phone-Use Agent Environments
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.