EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
EComAgentBench is introduced, a benchmark of 662 tasks grounded in real Amazon products and reviews that will serve as a reproducible foundation for moving shopping agents from single-query search toward dependable assistance over long horizons.
Ze-Yao Du, Tongxin Li, Yan-Ci Zhang et al.
· arXiv.org · 4 citations