HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 9 days ago • 60
Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers Paper • 2608.26762 • Published 15 days ago • 24
HelixWorld: A Real-time Interactive Audio-Visual World Model Paper • 2609.38123 • Published 12 days ago • 38
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 10 days ago • 282
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Paper • 2609.34981 • Published 12 days ago • 138
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published 13 days ago • 130
MaLiang-Harness: A Programmable Path to Image and Video Generation Paper • 2609.34309 • Published 13 days ago • 394
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Paper • 2609.34759 • Published 13 days ago • 153
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 15 days ago • 326
In-Context Learning for Robots: Methods and Applications Paper • 2609.36012 • Published 13 days ago • 322
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 14 days ago • 675
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR Paper • 2609.37868 • Published 12 days ago • 65