Toward Generative 6G Simulation: An Experimental Multi-Agent LLM and ns-3 Integration

TL;DR

The paper tackles the need for open, full-stack 6G simulations by introducing a generative framework that combines a coordinated set of LLM-driven agents with the ns-3 network simulator. It details a four-agent workflow that generates simulation scripts, designs automated test suites, executes simulations, and interprets results, all orchestrated via LangChain and retrieval-augmented techniques. A detailed 5G NR case study demonstrates how natural-language requirements can be transformed into validated ns-3 scripts, with iterative feedback improving code quality and simulation fidelity. The approach shows promise in accelerating full-stack network experimentation, though challenges remain in ensuring bug-free code, scaling, and keeping pace with evolving standards.

Abstract

The move toward open Sixth-Generation (6G) networks necessitates a novel approach to full-stack simulation environments for evaluating complex technology developments before prototyping and real-world implementation. This paper introduces an innovative approach\footnote{A lightweight, mock version of the code is available on GitHub at that combines a multi-agent framework with the Network Simulator 3 (ns-3) to automate and optimize the generation, debugging, execution, and analysis of complex 5G network scenarios. Our framework orchestrates a suite of specialized agents -- namely, the Simulation Generation Agent, Test Designer Agent, Test Executor Agent, and Result Interpretation Agent -- using advanced LangChain coordination. The Simulation Generation Agent employs a structured chain-of-thought (CoT) reasoning process, leveraging LLMs and retrieval-augmented generation (RAG) to translate natural language simulation specifications into precise ns-3 scripts. Concurrently, the Test Designer Agent generates comprehensive automated test suites by integrating knowledge retrieval techniques with dynamic test case synthesis. The Test Executor Agent dynamically deploys and runs simulations, managing dependencies and parsing detailed performance metrics. At the same time, the Result Interpretation Agent utilizes LLM-driven analysis to extract actionable insights from the simulation outputs. By integrating external resources such as library documentation and ns-3 testing frameworks, our experimental approach can enhance simulation accuracy and adaptability, reducing reliance on extensive programming expertise. A detailed case study using the ns-3 5G-LENA module validates the effectiveness of the proposed approach. The code generation process converges in an average of 1.8 iterations, has a syntax error rate of 17.0%, a mean response time of 7.3 seconds, and receives a human evaluation score of 7.5.

Figures (4)

• Figure 1: The graphical user interface of application.
• Figure 2: Overview of the multi-agent LLM-based ns-3 simulation framework. The streamlined workflow is shown in Figure \ref{['fig:Simulation_workflow']}.
• Figure 3: The sample ns-3 generated code.
• Figure 4: Sequence diagram illustrating the streamlined workflow for simulating a 5G NR environment.