While language agents have achieved promising success by placing Large
Language Models at the core of a more versatile design that dynamically
interacts with the external world, the existing approaches neglect the notion
of uncertainty during these interactions. We present the Uncertai
利用符号人工智能的代理设计历史,我们提出了一种新的认知语言代理的蓝图,即 Cognitive Architectures for Language Agents (CoALA) 框架,这个框架将大型语言模型与外部资源或内部控制流结合起来,以实现基于语言模型的推理、概念化、学习和决策。通过 CoALA 框架,我们强调了目前语言代理的不足,并提出了未来发展更强大的语言代理的具体方向。