Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.13402 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912278572433408 |
|---|---|
| author | Rezazadeh, Farhad Gargari, Amir Ashtari Lagen, Sandra Song, Houbing Niyato, Dusit Liu, Lingjia |
| author_facet | Rezazadeh, Farhad Gargari, Amir Ashtari Lagen, Sandra Song, Houbing Niyato, Dusit Liu, Lingjia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Toward Generative 6G Simulation: An Experimental Multi-Agent LLM and ns-3 Integration Rezazadeh, Farhad Gargari, Amir Ashtari Lagen, Sandra Song, Houbing Niyato, Dusit Liu, Lingjia Networking and Internet Architecture 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. |
| title | Toward Generative 6G Simulation: An Experimental Multi-Agent LLM and ns-3 Integration |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2503.13402 |