OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific Software Paper • 2609.39903 • Published Sep 30 • 28
Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? Paper • 2610.28763 • Published 24 days ago • 19
UI-Mate Collection Open-weight CUA models and office-centric CUA benchmark • 4 items • Updated 16 days ago • 22
Player-1: Learning to Play from Synthetic Experience Paper • 2610.20584 • Published about 1 month ago • 57
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience Paper • 2609.03241 • Published Sep 3 • 41
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks Paper • 2609.11042 • Published Sep 10 • 65
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Paper • 2608.15930 • Published Aug 16 • 48
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Paper • 2608.15930 • Published Aug 16 • 48
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published Jul 14 • 114
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Paper • 2606.11176 • Published Jun 9 • 131
ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation Paper • 2312.13108 • Published Dec 20, 2023 • 3
GUI Action Narrator: Where and When Did That Action Take Place? Paper • 2406.13719 • Published Jun 19, 2024
CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing Paper • 2605.19484 • Published May 19 • 21
CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing Paper • 2605.19484 • Published May 19 • 21