Leveraging Large Language Models for Automated Reproduction of Networking Research Results
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908833983496192 |
|---|---|
| author | Jiang, Yining Xu, Yunxin Xu, Wenyun Zhu, Yufan He, Tangtang Huang, Haiying Zhu, Letian Song, Qingyu Su, Qiang You, Lizhao Tang, Lu Feng, Wanjin Zhang, Yuchao Kong, Linghe Xiang, Qiao Shu, Jiwu |
| author_facet | Jiang, Yining Xu, Yunxin Xu, Wenyun Zhu, Yufan He, Tangtang Huang, Haiying Zhu, Letian Song, Qingyu Su, Qiang You, Lizhao Tang, Lu Feng, Wanjin Zhang, Yuchao Kong, Linghe Xiang, Qiao Shu, Jiwu |
| contents | Code reproduction is a cornerstone of scientific validity, yet it remains a formidable challenge in computer networking research due to the scarcity of open-source implementations and the complexity of heterogeneous system architectures. While Large Language Models have demonstrated potential in code generation, existing code generation frameworks often fail to address the long-context constraints and intricate logical dependencies required to reproduce network systems from academic papers. To facilitate result reproduction, we introduce \emph{RepLLM}, an end-to-end multi-agent framework designed to automate the transformation of network research into executable code. RepLLM features a novel collaborative architecture comprising four specialized agents -- Content Parsing, Architecture Design, Code Generation, and Audit \& Repair -- coordinated through an explicit \textit{Shared Memory} mechanism to ensure global context consistency. With the enhancement of Chain-of-Thought LLM reasoning and a sandbox-isolated static-dynamic debugging methodology, our framework effectively resolves semantic discrepancies and runtime errors. Extensive evaluations on representative papers from SIGCOMM and NSDI demonstrate that RepLLM significantly outperforms state-of-the-art baselines in generating compile-ready and logically correct systems. Results further demonstrate that RepLLM facilitates the reproduction of 80\% of the original benchmarks with only four hours of human intervention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21074 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Large Language Models for Automated Reproduction of Networking Research Results Jiang, Yining Xu, Yunxin Xu, Wenyun Zhu, Yufan He, Tangtang Huang, Haiying Zhu, Letian Song, Qingyu Su, Qiang You, Lizhao Tang, Lu Feng, Wanjin Zhang, Yuchao Kong, Linghe Xiang, Qiao Shu, Jiwu Networking and Internet Architecture Code reproduction is a cornerstone of scientific validity, yet it remains a formidable challenge in computer networking research due to the scarcity of open-source implementations and the complexity of heterogeneous system architectures. While Large Language Models have demonstrated potential in code generation, existing code generation frameworks often fail to address the long-context constraints and intricate logical dependencies required to reproduce network systems from academic papers. To facilitate result reproduction, we introduce \emph{RepLLM}, an end-to-end multi-agent framework designed to automate the transformation of network research into executable code. RepLLM features a novel collaborative architecture comprising four specialized agents -- Content Parsing, Architecture Design, Code Generation, and Audit \& Repair -- coordinated through an explicit \textit{Shared Memory} mechanism to ensure global context consistency. With the enhancement of Chain-of-Thought LLM reasoning and a sandbox-isolated static-dynamic debugging methodology, our framework effectively resolves semantic discrepancies and runtime errors. Extensive evaluations on representative papers from SIGCOMM and NSDI demonstrate that RepLLM significantly outperforms state-of-the-art baselines in generating compile-ready and logically correct systems. Results further demonstrate that RepLLM facilitates the reproduction of 80\% of the original benchmarks with only four hours of human intervention. |
| title | Leveraging Large Language Models for Automated Reproduction of Networking Research Results |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2509.21074 |