CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking

这条英文动态主要涉及智能体工作流、评测与基准。原文要点：Recent benchmarks rely on user simulators to evaluate AI agents in multi-turn interaction. While existing simulation techniques demonstrate surface fidelity to human style and behavior, ecologically valid interactive benchmarking also requires alignment in when and how agents fail across simulated and real user populations. We find that existing simulators lack outcome calibration: agreement with observed success rat...