Conversational Orchestration for Organic 6G
作者: Masoud Shokrnezhad, Tarik Taleb
分类: cs.NI, cs.AI, cs.DC, cs.ET, cs.MA
发布日期: 2026-08-11
备注: 7 pages, 6 figures. Accepted for publication in IEEE Network Magazine
💡 一句话要点
提出轻量级去中心化对话编排框架以解决Organic 6G服务问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: Organic 6G 去中心化编排 大型语言模型 域代理 服务提供 控制平面开销 动态变化
📋 核心要点
- 现有跨域编排方法依赖复杂的集成架构,导致部署困难和协调开销增加。
- 提出了一种轻量级去中心化的对话编排框架,利用大型语言模型驱动的域代理实现自治和高效协作。
- 仿真结果表明,控制平面开销可控,决策质量稳健,能够有效应对域的动态变化。
📝 摘要(中文)
Organic 6G愿景要求在边缘云连续体和非地面资源的支持下,实现简单、可扩展且灵活的服务提供。尽管跨域编排已有进展,但现有方案往往依赖于复杂的集成架构和深度遥测管道,导致部署困难和协调开销增加。本文提出了一种基于大型语言模型(LLM)驱动的去中心化对话编排框架,使每个域保持自主性。代理通过工具观察本地状态,进行闭环推理,并通过代理间(A2A)覆盖网络与邻近代理交换摘要。通过周期性传播可达性广告,快速实现可行的资源配置,同时通过事件驱动请求和协商处理安全的重新优化、扩展和迁移。仿真结果显示,随着域的扩展和加入,控制平面开销可控且决策质量稳健。
🔬 方法详解
问题定义:本文旨在解决Organic 6G中服务提供的复杂性和协调开销问题。现有方法通常依赖重型集成架构,难以实现灵活和可扩展的服务编排。
核心思路:提出了一种基于大型语言模型(LLM)的去中心化对话编排框架,使每个域保持自主性,代理通过观察和推理实现高效协作。
技术框架:整体架构包括域代理、代理间覆盖网络(A2A)和事件驱动请求机制。代理观察本地状态,进行闭环推理,并与邻近代理交换信息。
关键创新:最重要的创新在于去中心化的设计和基于LLM的推理能力,使得系统能够在域动态变化时保持高效和灵活。
关键设计:采用周期性传播可达性广告(如延迟、瓶颈带宽和计算能力),并通过事件驱动的请求和协商机制处理资源的重新优化和迁移。
🖼️ 关键图片
📊 实验亮点
实验结果显示,随着域的扩展,控制平面开销保持在可管理的范围内,且决策质量在目标变化后能够快速恢复。具体而言,控制平面开销接近线性增长,显示出良好的可扩展性。
🎯 应用场景
该研究的潜在应用领域包括未来的6G网络架构、智能城市、无人驾驶和物联网等场景。通过实现高效的服务编排,可以显著提升网络资源的利用率和服务质量,推动各类新兴应用的发展。
📄 摘要(原文)
The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its promise, service provisioning that is simple to operate, scalable across independently administered domains, and agile under domain churn (i.e., domains dynamically joining and leaving). Despite advances in cross-domain orchestration, many proposals rely on heavy integration fabrics, multi-layer coordinators, and deep telemetry pipelines that hinder deployability and amplify coordination overhead. We propose a lightweight, decentralized conversational orchestration framework based on Large Language Model (LLM)-driven domain agents. Each domain remains autonomous: an agent observes local state via tools, reasons in a closed loop, and exchanges summaries with neighboring agents over an Agent-to-Agent (A2A) overlay aligned with data-plane coupling. Fast feasible placement is enabled by periodic, routing-like dissemination of reachability advertisements (latency, bottleneck bandwidth, and compute capacity), while safe re-optimization, scaling, and migration are handled through event-driven requests and negotiation. To meet real-time constraints, we deploy a compact reasoning model trained with verifier-based self-verification and periodically refined online via shadow updates. Simulations show manageable, near-linear control-plane overhead as domains scale and during domain joins, and robust decision quality, including recovery after objective changes. We close by outlining future research directions for principled, secure, and uncertainty-aware agentic orchestration in Organic 6G.