让不同技术的AI能自然对话，支持多人协作讨论
AI Multi-Agent Interoperability Extension for Managing Multiparty Conversations
- 提出通用自然语言接口，统一异构AI通信标准
- 设计会议主持人、发言权管理等机制，支持多智能体协同
- 适合需要多方AI协作的场景，如智能会议、联合决策
本文提出对开放语音互操作倡议（OVON）现有多智能体互操作规范的扩展，使采用不同技术开发的AI智能体可通过通用自然语言接口或基于NLP的标准接口进行通信。聚焦于多参与者对话管理，引入会话召集者（Convener Agent）、共享发言权对话空间、发言权管理者、多参与方支持机制，以及处理打断和未邀请参与者的方法。同时探讨了会话召集者作为消息中继与交互控制者的角色，提升了系统的可扩展性与安全性。这些改进对于实现多个AI智能体在协作、辩论或共同讨论等场景下的流畅、高效与安全交互至关重要。论文详细阐述了相关概念，并通过实例展示其在对话封装结构中的应用。
原文摘要 · Abstract (English)
This paper presents a novel extension to the existing Multi-Agent Interoperability specifications of the Open Voice Interoperability Initiative (originally also known as OVON from the Open Voice Network). This extension enables AI agents developed with different technologies to communicate using a universal, natural language-based API or NLP-based standard APIs. Focusing on the management of multiparty AI conversations, this work introduces new concepts such as the Convener Agent, Floor-Shared Conversational Space, Floor Manager, Multi-Conversant Support, and mechanisms for handling Interruptions and Uninvited Agents. Additionally, it explores the Convener's role as a message relay and controller of participant interactions, enhancing both scalability and security. These advancements are crucial for ensuring smooth, efficient, and secure interactions in scenarios where multiple AI agents need to collaborate, debate, or contribute to a discussion. The paper elaborates on these concepts and provides practical examples, illustrating their implementation within the conversation envelope structure.
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。