让AI agent像人一样异步处理任务，实时响应操作。
Asynchronous Tool Usage for Real-Time Agents
- 用事件驱动的状态机架构实现并行执行与实时响应。
- 结合语音识别与语音合成，支持连续交互不卡顿。
- 适合需要高响应性、多任务的智能助手场景。
尽管前沿大语言模型具备工具使用能力，但当前AI系统仍采用严格的轮次制模式，对时间流逝视而不见。这种同步设计强制用户请求与工具调用顺序进行，无法实现多任务处理，降低交互性。为解决此问题，我们提出可异步运行的AI代理，支持并行处理与实时工具使用。核心贡献是将事件驱动的有限状态机架构用于代理执行与提示生成，并集成自动语音识别与文本转语音技术。受实时操作系统概念启发，本研究既提供概念框架，也给出可落地的工具，推动实现流畅、多任务的智能交互。
原文摘要 · Abstract (English)
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.
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。