Abstract
While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synchronous design forces user queries and tool-use to occur sequentially, preventing the systems from multitasking and reducing interactivity. To address this limitation, we introduce asynchronous AI agents capable of parallel processing and real-time tool-use. Our key contribution is an event-driven finite-state machine architecture for agent execution and prompting, integrated with automatic speech recognition and text-to-speech. Drawing inspiration from the concepts originally developed for real-time operating systems, this work presents both a conceptual framework and practical tools for creating AI agents capable of fluid, multitasking interactions.
Abstract (translated)
尽管前沿的大语言模型（LLMs）是能够使用工具的智能代理，当前的人工智能系统仍然以严格的回合制方式运行，对时间的流逝毫无察觉。这种同步设计迫使用户查询和工具使用顺序进行，从而阻止了系统的多任务处理并降低了互动性。为了解决这一限制，我们引入了能够并行处理和实时使用工具的异步AI代理。我们的主要贡献是一种基于事件驱动的有限状态机架构，用于代理执行和提示，并与自动语音识别及文本转语音技术集成在一起。借鉴最初为实时操作系统开发的概念，本工作既提出了一个概念框架，也提供了实用工具，以创建能够进行流畅多任务互动的AI代理。
URL
https://arxiv.org/abs/2410.21620
