从AI代理演示到生产：模拟驱动的自动化测试与评估
原标题：Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation
AI 摘要
哥伦比亚大学教授兼Arklex AI联合创始人周宇在演讲中探讨了如何将AI代理从演示推向生产，重点介绍了模拟驱动的测试与改进方法。她以沃尔玛的Sparky和亚马逊的Rufus等购物代理为例，展示了对话代理如何通过工具集成和上下文理解提升用户体验，并现场演示了一个语音代理处理信用卡申请的完整流程。她指出95%的代理仍停留在演示阶段，强调通过模拟环境进行自动化测试和评估对于实现真实价值的重要性。
正文节选
Transcript Zhou Yu: Today I'm going to talk about simulation-driven AI agent testing and improvement. A little bit of background. I'm the co-founder of Arklex AI. I'm also a professor at Columbia University. I've been working on AI for quite a long time. I've been a professor for nine years. I've been working with various open-source models for pre-training, post-training, and so on. One of the things I really cared about is how do these models actually get into production? How can we actually u