4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes Paper • 2610.03715 • Published 11 days ago • 34
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 12 days ago • 285
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published 11 days ago • 60
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Paper • 2609.32259 • Published 14 days ago • 101
Smaller Models, Better Rejects: Preference Distillation Scaling Paper • 2609.38987 • Published 13 days ago • 32
Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts Paper • 2610.00314 • Published 14 days ago • 103