返回全部动态
DoorDash 从模型到智能体：构建大规模上下文感知消费者 AI
原标题：Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
AI 摘要
DoorDash 机器学习与 AI 负责人 Sudeep Das 在 QCon AI 大会上分享了公司从传统一次性预测向智能体推荐平台转型的经验。他介绍了利用语言原生消费者记忆、RQ-VAE 语义 ID 进行目录表示以及基于检索的搜索，显著提升了相关性和转化率指标。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
InfoQ Homepage Presentations From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash Summary Sudeep Das shares how DoorDash shifts from legacy one-shot predictions to an agentic recommendation platform. He discusses leveraging language-native consumer memory, RQ-VAE semantic IDs for catalog representation, and grounded search to dramatically boost relevance and conversion metrics. Bio Sudeep Das
发布时间：2026-08-15 19:00
抓取时间：2026-08-15 19:41
来源机构：InfoQ