arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09007cs.ITcs.AImath.IT
收藏

LLMind:利用 LLM 协调 AI 与 IoT 以执行复杂任务

LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution

The Chinese University of Hong Kong(香港中文大学);University of Macau(澳门大学);Imperial College London(伦敦帝国学院)

Hongwei Cui, Yuyang Du, Qun Yang, Yulin Shao, Soung Chang Liew

AI总结:

本文提出基于 LLM 的 AI 智能体框架 LLMind,通过语言—FSM—代码转换生成控制脚本,协调 IoT 设备与领域 AI 模块执行复杂任务,并以经验积累机制持续优化。

摘要:

面向任务的通信是未来智能 IoT 系统的重要组成部分。然而,现有 IoT 系统在处理复杂任务方面能力有限,尤其是在与人类交互以完成这些任务方面。本文提出 LLMind,这是一个基于 LLM 的面向任务的 AI 智能体框架,可实现 IoT 设备之间的有效协作,并由人类传达高层口头指令以执行复杂任务。受大脑功能专门化理论启发,该框架将 LLM 与特定领域 AI 模块集成,以增强其能力。复杂任务可能涉及多个特定领域 AI 模块和 IoT 设备的协作,这些任务通过 LLM 使用语言—代码转换方法生成的控制脚本来执行;该方法首先将语言描述转换为中间有限状态机(FSM),随后再精确转换为代码。此外,该框架引入了一种新颖的经验积累机制,以提升响应速度和有效性,使框架能够通过持续的用户与机器交互不断演化并逐渐成熟。

英文摘要:

Task-oriented communications are an important element in future intelligent IoT systems. Existing IoT systems, however, are limited in their capacity to handle complex tasks, particularly in their interactions with humans to accomplish these tasks. In this paper, we present LLMind, an LLM-based task-oriented AI agent framework that enables effective collaboration among IoT devices, with humans communicating high-level verbal instructions, to perform complex tasks. Inspired by the functional specialization theory of the brain, our framework integrates an LLM with domain-specific AI modules, enhancing its capabilities. Complex tasks, which may involve collaborations of multiple domain-specific AI modules and IoT devices, are executed through a control script generated by the LLM using a Language-Code transformation approach, which first converts language descriptions to an intermediate finite-state machine (FSM) before final precise transformation to code. Furthermore, the framework incorporates a novel experience accumulation mechanism to enhance response speed and effectiveness, allowing the framework to evolve and become progressively sophisticated through continuing user and machine interactions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑