FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 10 days ago • 63
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Paper • 2611.03126 • Published 12 days ago • 51
Towards Agentic Robots: Model, Data, Environment, and Harness Paper • 2610.20442 • Published Oct 14 • 33
ReTerm: Recovery Training for Self-Improving Terminal Agents Paper • 2610.18484 • Published Oct 13 • 17
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video Paper • 2610.12419 • Published Oct 8 • 23
FrontierPhysics: Evaluating Agents for End-to-End Physics Research Paper • 2611.06910 • Published 10 days ago • 63
VideoMemBench: How Well Do MLLMs Remember in Video Conversations? Paper • 2610.40131 • Published 11 days ago • 35
CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements Paper • 2611.03126 • Published 12 days ago • 51
WorldCast: Exploring Intelligent Visual Generation in World State Prediction Paper • 2610.20731 • Published Oct 14 • 34
Towards Agentic Robots: Model, Data, Environment, and Harness Paper • 2610.20442 • Published Oct 14 • 33
Towards Agentic Robots: Model, Data, Environment, and Harness Paper • 2610.20442 • Published Oct 14 • 33
ReTerm: Recovery Training for Self-Improving Terminal Agents Paper • 2610.18484 • Published Oct 13 • 17
ReTerm: Recovery Training for Self-Improving Terminal Agents Paper • 2610.18484 • Published Oct 13 • 17
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video Paper • 2610.12419 • Published Oct 8 • 23
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published Jul 26 • 84
SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation Paper • 2607.05943 • Published Jul 7 • 16