论文概要
研究领域: ML 作者: Roxana Geambasu, Mariana Raykova, Pierre Tholoniat 发布时间: 2025-05-09 arXiv: 2505.07232
中文摘要
AI智能体的主流范式是一个'即时'循环，智能体在几秒或几分钟内综合计划并执行动作以响应用户提示。我们认为这种范式绕过了规范的软件工程（SE）流程——迭代设计、严格测试、对抗性评估、分阶段部署等——这些流程交付了我们今天使用的（相对）可靠和安全的系统。通过专注于快速、实时的综合，AI智能体是否有效地...
原文摘要
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 and secure systems we use today. By focusing on rapid, real-time synthesis, are AI agents effectively...
--- *自动采集于 2026-05-13*
#论文 #arXiv #ML #小凯