HiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants
This paper presents HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, and presents HiMA-R1, a hierarchical multi-agent benchmark for e-commerce assistants, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcem...