核心信息
Qwen 推出 E-Commerce Bench 基准,用于评估 AI 智能体在长期自主商业运营中的表现:智能体以 10 万元启动资金运营网店 365 个模拟日,需处理选品、询价、定价、促销、库存和现金流,市场由真实电商数据驱动。
要点
- 基于真实经济数据:6886 件商品、576 家供应商(其中 152 家为欺诈方),包含仓储费、退货和信誉机制。
- 核心难点是长期推理:几乎没有模型学会以更低成本采购或随时间改进策略,为专用商业任务优化提供参考。
Qwen 推出 E-Commerce Bench 基准,用于评估 AI 智能体在长期自主商业运营中的表现:智能体以 10 万元启动资金运营网店 365 个模拟日,需处理选品、询价、定价、促销、库存和现金流,市场由真实电商数据驱动。
E-Commerce Bench is a small attempt to evaluate models in a specific business setting. hope it can offer a useful reference for improving model performance on specialized business tasks.
Meet E-Commerce Bench, a new benchmark for long-horizon autonomous business operations. 🚀 Agents start with ¥100,000 to run online stores for 365 days, handling sourcing, negotiation, pricing, promotions, inventory and cash flow, in a market driven by real e-commerce data. What's inside: 👀 - Real economics: 6886 products, 576 suppliers (152 fraudsters), 600-minute workdays, storage fees, returns and reputation. - Long-horizon learning: almost no model learns to buy cheaper or improve its strategies over a full year of operation. - Seven-axis evaluation: beyond year-end assets, we score six more dimensions, revealing that no single model dominates across the board. Learn more about E-Commerce Bench: 👇 - Blog: https://t.co/fpdO9jwwiV - Paper: https://t.co/EYIGlMPFUn - Project: https://t.co/ss2kuThRin - Code: https://t.co/xZOURdp7zE