RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 12 days ago • 284
4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes Paper • 2610.03715 • Published 11 days ago • 34
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published 17 days ago • 326
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression Paper • 2609.36322 • Published 15 days ago • 116
EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? Paper • 2609.37686 • Published 14 days ago • 72
Follow the Entities: A Corpus Map for Agentic Search Paper • 2609.37226 • Published 14 days ago • 100