UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents Paper • 2610.30932 • Published 5 days ago • 49
UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents Paper • 2610.30932 • Published 5 days ago • 49
ReportLogic: Evaluating Logical Quality in Deep Research Reports Paper • 2602.18446 • Published Jan 27