AgenticNet: Utilizing AI Coding Agents To Create Hybrid Network Experiments

2026-03-24

AI Summary

This work proposes a next-generation network experimentation framework based on AI-encoded agents to overcome the limitations of traditional platforms, which struggle to balance flexibility between simulation and physical testing, thereby hindering research efficiency in complex scenarios. The proposed platform seamlessly integrates simulation, physical, and hybrid execution modes for the first time, leveraging a cooperative implementation in Python and C++. AI agents autonomously orchestrate heterogeneous components across these modes. Experimental results demonstrate that the C++ implementation surpasses the Python variant in both accuracy and performance, validating the effectiveness and efficiency of the hybrid experimental architecture. This advancement significantly enhances prototyping speed and experimental flexibility, offering a robust foundation for future network research and development.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Traditional network experiments focus on validation through either simulation or emulation. Each approach has its own advantages and limitations. In this work, we present a new tool for next-generation network experiments created through Artificial Intelligence (AI) coding agents. This tool facilitates hybrid network experimentation through simulation and emulation capabilities. The simulator supports three main operation modes: pure simulation, pure emulation, and hybrid mode. AgenticNet provides a more flexible approach to creating experiments for cases that may require a combination of simulation and emulation. In addition, AgenticNet supports rapid development through AI agents. We test Python and C++ versions. The results show that C++ achieves higher accuracy and better performance than the Python version.

Problem

• network experiments
• simulation
• emulation
• hybrid experimentation

Innovation

• AI coding agents
• hybrid network experimentation
• simulation and emulation
• AgenticNet
• network experiment automation