A compact reasoning model trained with verifier-based self-verification and periodically refined online via shadow updates is deployed, showing manageable, near-linear control-plane overhead as domains scale and during domain joins, and robust decision quality, including recovery after objective changes.
Abstract
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.
The 6G era introduces unprecedented complexity in managing heterogeneous, large-scale, and dynamic network infrastructures. These challenges are addressed by the concept of Intent-Based Networking (IBN), which has emerged as a promising paradigm for autonomous network management, enabling users to express high-level objectives that are automatically translated and enforced by the network. However, current IBN solutions remain constrained by rigid structured specifications and limited assurance mechanisms. This paper presents an overview of PhD research leveraging Generative AI (GenAI), specifically Large Language Models (LLMs), to address three fundamental IBN challenges: (i) intent translation, (ii) intent assurance, and (iii) GenAI operations in IBN systems. We propose a set of novel frameworks validated on real 5G/6G testbeds. Most contributions are supported by demos, datasets, and open-source implementations, which are referenced in the design section of each contribution. This PhD positions GenAI as a key enabler for advancing autonomous and user-centric 6G.
The evolution towards 6G edge-cloud ecosystems demands autonomous, intent-based network management to handle unprecedented infrastructure complexity. While Large Language Models offer promising capabilities for translating high-level user intents into network configurations, current monolithic approaches suffer from cognitive overload, hallucinations, and a profound inability to safely execute low-level data plane mutations. To bridge this gap, we introduce Edgent, a novel framework that integrates hierarchical Agentic AI with Extended Berkeley Packet Filter technologies via the Model Context Protocol. Edgent utilizes a state-driven Supervisor, enhanced by Retrieval-Augmented Generation, to decompose abstract human intents into deterministic execution graphs and dynamically delegate tasks to domain-specific worker agents. We empirically validate the framework by autonomously deploying a distributed, in-kernel DDoS mitigation pipeline across scaled containerized topologies containing up to 85 nodes. Extensive evaluations demonstrate high orchestration reliability; notably, even heavily quantized Small Language Models (e.g., 4B parameters) achieve near-perfect zero-shot execution and 100% overall task completion through autonomous error recovery. Finally, latency and resource profiling confirm that the multi-agent framework can be efficiently driven by fully localized models compatible with orchestration tasks directly within resource-constrained edge environments, therefore this work positions Edgent as a pragmatic step toward the realization of zero-touch nextgeneration networks.
Raffaele Di Tommaso, G. Davoli, Pietro Spadaccino et al.· IEEE Conference on Network S...· 0 citations
As Software-Defined Networking (SDN) and Network Function Virtualization (NFV) enabled networks scale in size and complexity, monitoring and managing Service Function Chains (SFCs) under stringent latency and resource constraints becomes increasingly challenging. Although Deep Reinforcement Learning (DRL) is widely applied to SFC provisioning and Virtual Network Function (VNF) placement, enhanced network state monitoring is crucial to capture unexpected network conditions and guide DRL agents toward more adaptive decisions. In this context, Language Models (LMs) enable flexible, natural-language (NL)–based, query-driven network monitoring; however, directly processing complex multi-metric NL queries is computationally expensive and error-prone. This paper proposes an end-to-end (E2E) edge-based query translation pipeline that decomposes multi-metric NL queries into simpler single-metric sub-queries. Query decomposition is performed using a retrieval-augmented language model (RAG-LLM) and compared with a lightweight rule-based decomposition baseline. The resulting sub-queries are translated into Structured Query Language (SQL) using FLAN-T5. A cloud-only baseline, which directly translates NL queries to SQL without decomposition, is also evaluated. The results show that the rule-based edge pipeline achieves the lowest latency, reducing E2E latency by up to 78% compared to RAG-LLM and 18% compared to cloud execution under high workloads. Under increasing arrival rates for the largest workload, the rule-based edge pipeline maintains superior performance over cloud, reducing total E2E latency by 57% at $\lambda = 0.8$ . While RAG-LLM provides greater flexibility for unseen query patterns, both edge-based approaches achieve 100% NL2SQL accuracy with zero decomposition failures, outperforming the cloud-only baseline (95% accuracy).
Parisa Fard Moshiri, Xinyu Zhu, Poonam Lohan et al.· IEEE Transactions on Network...· 0 citations
Network intelligence has largely evolved around logically centralized control and orchestration. Although this model simplifies coordination, it creates a critical dependency on centralized services and limits localized adaptation. This paper presents Agentic-Defined Networking (ADN), an architecture that treats autonomous Artificial Intelligence agents as first-class entities embedded across the network infrastructure. ADN has two defining properties. First, agents perceive local state, maintain beliefs, reason over operator-defined objectives, coordinate with peers, and actuate programmable resources without requiring a persistent central controller in the critical decision path. Second, the mapping between agents and infrastructure is a deployment choice, supporting device-level, cluster-level, and hierarchical configurations. We formalize the ADN agent model and workflow and define an operational framework covering communication, lifecycle management, governance, and security. We evaluate feasibility and scaling through Mininet-AI experiments with topologies of up to 200 switches. The results characterize routing throughput, reasoning latency, fault-mitigation time, and coordination cost under distributed and hierarchical configurations. The study provides initial evidence of feasibility while identifying the challenges that must be addressed before production deployment.
F. Rossi, Paulo Silas Severo De Souza, Diogo Mainart Monteiro et al.· IEEE Access· 0 citations
Efficient Service Function Chaining (SFC) orchestration in large-scale NFV environments is often bottlenecked by the non-linear overhead of traditional Graph Convolutional Networks (GCNs). This paper proposes GraphSAGE-DQN, a scalable algorithm that leverages inductive neighbor sampling to decouple state extraction complexity from network size, achieving linear computational complexity. By integrating GraphSAGE embeddings with a Deep Q-Network (DQN), the model optimizes deployment strategies to maximize request acceptance rates. Simulations show that GraphSAGE-DQN outperforms traditional DQN and SECA algorithms, particularly in high-load scenarios where it improves acceptance rates by $\mathbf{1. 6 4 \%}$ and $\mathbf{1 7. 0 \%}$, respectively. These results confirm the model's efficiency and scalability for dynamic SFC orchestration in large-scale networks.
In today's fast-paced environment, the ability to swiftly access, understand, and act on data is no longer optional; it is essential. Yet most organizations remain data-rich but insight-poor, constrained by the complexity of querying, interpreting, and explaining enterprise-scale information. We present Polaris, a supervisor-led multi-agent framework for conversational enterprise analytics that bridges this gap. Polaris introduces Dynamic Task Coordination (DTC), a decision-theoretic orchestration layer that models agent-task assignment as adaptive bipartite matching, enabling real-time coordination, recovery, and optimization across specialized agents for querying, visualization, and reasoning. By coupling DTC with reason-first, ReAct-style agents, Polaris transforms natural-language queries into coherent analytical workflows that not only retrieve and visualize data but also explain the underlying"why."Evaluation on structured enterprise datasets demonstrates high semantic fidelity and answer relevancy, underscoring the potential of multi-agent orchestration to deliver trustworthy, end-to-end business intelligence at scale.
K. VaruniH., Soham Sarkar, Jay Kumar et al.· 0 citations