沃尔玛分享大规模批量智能：高性价比多智能体 LLM 工作流
原标题：Presentation: Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience
AI 摘要
沃尔玛全球科技高级软件工程师 Aditya Mulik 在 InfoQ 分享了一个面向零售库存预测的多智能体 LLM 工作流方案。该方案在沃尔玛已有的基于历史销售数据的机器学习预测模型之上，叠加顺序执行的多智能体编排，由不同智能体分别从 BigQuery 等数据源采集上下文、整合历史销售数据，以应对暴风雨等历史趋势无法覆盖的突发情况。其目标是提升约 4700 家门店、数十万 SKU 场景下的库存准确率，减少缺货与生鲜过期浪费。
正文节选
Transcript Aditya Mulik: My topic today is, Batch Intelligence at Scale, which is, Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience. My name is Aditya Mulik. I work as a senior software engineer at Walmart Global Tech. The problem I want to walk you through today is one which all retailers are wrestling with right now, which is inventory accuracy. What I want to say is the retail at massive scale, so Walmart has around 4,700 stores within the U.S. They have multiple stores in Ca