OSWorld-Verified

Search everything

Mentions · 7d0
Mentions · 30d4
All mentions4
First seenSep 30, 2026
Last mentioned11d ago

Timeline

4 articles · newest first

OS-Helix trains computer-use agents to mix GUI and code

OS-Helix-27B-RL reaches 66.44% on OSWorld-Verified, a further 42.9% relative gain after RL.

Hugging Face daily papersOct 14, 20:00 UTC · 11d agoAI research1 · 1 read

MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

MAI-Gym unifies GUI-agent evaluation and online RL; its 9B agent scores 78.4% on MobileWorld.

Hugging Face daily papersOct 13, 20:00 UTC · 12d agoAI research1 · 1 read

Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction

Work2Skill turns human GUI demos into reusable skills that raise computer-use agent scores.

Hugging Face daily papersOct 8, 20:00 UTC · 17d agoAI research1 · 1 read

GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution

GUI-HARVEST evolves GUI agent harnesses, lifting frozen Qwen3-VL by 12.33 points on OSWorld.

Hugging Face daily papersSep 30, 20:00 UTC · 25d agoAI research2

Appears with

WindowsAgentArenaproduct · 2
GPT-5ai model · 1
MAI-Gymproduct · 1
WorkDemo-350product · 1
OS-Helix-27B-RLai model · 1
Work2Skillproduct · 1
Qwen3-VL-32B-Instructai model · 1
MobileWorldproduct · 1
OS-Helix-27Bai model · 1
MAI-Gym-9Bai model · 1
WorkRecorderproduct · 1
OS-Helix-35B-A3Bai model · 1
MyPCBenchproduct · 1
Qwen3.5ai model · 1

Entities are extracted by the model from each article. First seen Sep 30, 2026, last mentioned 11d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.