Jul 2026
MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents
This work introduces MMShopBench, the first real-log benchmark for multimodal, multi-turn shopping agents, and builds an offline shopping sandbox, where fine-tuning substantially narrows the performance gap between the open-source model and leading proprietary models.
Zeying Hao, Haoze Guo, Meng-Tao Xu et al.
· arXiv.org · 0 citations