Research
UserArena benchmark tests shopping agents on real e-commerce user trajectories
UserArena contains 64,729 session trajectories from 11,010 users across 566,102 items and 13 action types. It introduces On-Policy Trajectory Distillation (OPTD), which the authors say gives the strongest simulator fidelity among those evaluated.
Every outlet that ran it 1 article
Hugging Face PapersResearchLead
UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents