FlexNGIA 2.0: Redesigning the Internet with Agentic AI - Protocols, Services, and Traffic Engineering Designed, Deployed, and Managed by AI

2025-09-02

AI Summary

The surge in immersive communication demands and the increasing dynamism and complexity of network environments pose significant challenges in protocol design, service orchestration, and traffic optimization. To address these, this paper proposes FlexNGIA 2.0—the first large language model (LLM)-driven, full-stack autonomous intelligent networking architecture. Methodologically, it introduces a multi-agent AI system endowed with perception, reasoning, and collaborative capabilities, integrating generative reasoning, tool-augmented execution, and network soft-orchestration to enable end-to-end autonomous generation and dynamic optimization of protocols, service chains, and congestion control policies. Experimental results demonstrate substantial improvements in network performance, reliability, and resource efficiency. FlexNGIA 2.0 advances the Internet toward a cognitive, self-evolving paradigm, establishing a foundational framework for LLM-native network intelligence.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The escalating demands of immersive communications, alongside advances in network softwarization and AI-driven cognition and generative reasoning, create a pivotal opportunity to rethink and reshape the future Internet. In this context, we introduce in this paper, FlexNGIA 2.0, an Agentic AI-driven Internet architecture that leverages LLM-based AI agents to autonomously orchestrate, configure, and evolve the network. These agents can, at runtime, perceive, reason, coordinate among themselves to dynamically design, implement, deploy, and adapt communication protocols, Service Function Chains (SFCs), network functions, resource allocation strategies, congestion control, and traffic engineering schemes, thereby ensuring optimal performance, reliability, and efficiency under evolving conditions. The paper first outlines the overall architecture of FlexNGIA 2.0 and its constituent LLM-Based AI agents. For each agent, we detail its design, implementation, inputs and outputs, prompt structures, interactions with tools and other agents, followed by preliminary proof-of-concept experiments demonstrating its operation and potential. The results clearly highlight the ability of these LLM-based AI agents to automate the design, the implementation, the deployment, and the performance evaluation of transport protocols, service function chains, network functions, congestion control schemes, and resource allocation strategies. FlexNGIA 2.0 paves the way for a new class of Agentic AI-Driven networks, where fully cognitive, self-evolving AI agents can autonomously design, implement, adapt and optimize the network's protocols, algorithms, and behaviors to efficiently operate across complex, dynamic, and heterogeneous environments. To bring this vision to reality, we also identify key research challenges toward achieving fully autonomous, adaptive, and agentic AI-driven networks.

Problem

• Redesigning Internet architecture using AI agents
• Autonomous orchestration of network protocols and services
• Dynamic adaptation of traffic engineering for optimal performance

Innovation

• AI agents autonomously orchestrate network protocols and services
• LLM-based agents dynamically design and adapt traffic engineering
• Cognitive AI agents self-evolve network functions and resource allocation