RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations Paper • 2610.01780 • Published 11 days ago • 283
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI Paper • 2609.38143 • Published 13 days ago • 85
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning Paper • 2609.03430 • Published Sep 3 • 188