RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 21 days ago • 290
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 20 days ago • 60
Multilingual GSM-Symbolic: What determines capability transfer across languages? Paper • 2610.03367 • Published 20 days ago • 52
HelixWorld: A Real-time Interactive Audio-Visual World Model Paper • 2609.38123 • Published 23 days ago • 38
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics Paper • 2609.36608 • Published 23 days ago • 8
FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets Paper • 2609.35770 • Published 24 days ago • 9
When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections Paper • 2609.32488 • Published 26 days ago • 27
Follow the Entities: A Corpus Map for Agentic Search Paper • 2609.37226 • Published 23 days ago • 101
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation Paper • 2609.34759 • Published 24 days ago • 152
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 26 days ago • 328
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 25 days ago • 749
In-Context Learning for Robots: Methods and Applications Paper • 2609.36012 • Published 24 days ago • 439