让AI学会自我评估，动态分配资源以提升效率与安全。
Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI
- AI主动监控自身状态，根据任务难度调整资源使用。
- 在联邦学习中显著提升学习效率与系统安全性。
- 提供可部署的框架，支持社区开发自省型AI应用。
本文主张将元认知作为构建更准确、安全和高效AI的通用设计原则。元认知方案要求系统监测自身状态，并依据问题实例的难度或出错成本，智能分配资源。借鉴资源理性AI及心理学中已验证的元认知策略，论文识别了将这些策略融入AI设计的具体挑战，指出了开放的理论与实现问题。通过一个联邦学习（FL）案例研究，展示了该原则如何提升学习效率、效果与安全性。同时，论文提出一个专为支持元认知型AI应用设计的新软件框架，便于社区进行设计、部署与实验。
原文摘要 · Abstract (English)
This position paper argues for metacognition as a general design principle for creating more accurate, secure, and efficient AI. The metacognitive solution involves systems monitoring their own states and judiciously allocating resources depending on each problem instance's difficulty or cost of mistakes. Drawing inspiration both from past work on resource-rational AI and from well-documented metacognitive strategies in psychology and cognitive science, we identify specific challenges in embedding these strategies into AI design and highlight open theoretical and implementation problems. We showcase these principles through a tangible example of improved learning efficiency, effectiveness, and security in a Federated Learning (FL) case study. We show how these principles can be translated into practice with a novel software framework developed specifically to allow the community to design, deploy, and experiment with metacognition-enabled AI applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。