**摘要**
The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts. We argue that this paradigm short-circuits disciplined software engineering (SE) processes -- iterative design, rigorous testing, adversarial evaluation, staged deployment, and more -- that have delivered the (relatively) reliable a
👤 作者: Roxana Geambasu, Mariana Raykova, Pierre Tholoniat, Trishita Tiwari, Lillian Tsai, Wen Zhang

---
🔗 **[Engineering Robustness into Personal Agents with the AI Workflow Store](https://arxiv.org/abs/2605.10907v1)**

> Engineering Robustness into Personal Agents with the AI Workflow Store
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-13 08:01