UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents Paper • 2610.30932 • Published about 1 month ago • 55
EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory Paper • 2610.10533 • Published Oct 7 • 9
AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation Paper • 2601.17761 • Published Jan 25 • 14
One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment Paper • 2601.18731 • Published Jan 26 • 7