CP-AgentNet: Autonomous and Explainable Communication Protocol Design Using Generative Agents

• Published in: Proceedings - International Conference on Network Protocols pp. 1 - 12
• Main Authors: Kwon, Dae Cheol, Zhang, Xinyu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22.09.2025
• Subjects: Autonomous systems; Communication networks; Complex networks; Data models; Decision making; Deep reinforcement learning; Faces; Neural networks; Protocols
• ISSN: 2643-3303
• DOI: 10.1109/ICNP65844.2025.11192445

Although DRL (deep reinforcement learning) has emerged as a powerful tool for making better decisions than existing hand-crafted communication protocols, it faces significant limitations: 1) Selecting the appropriate neural network architecture and setting hyperparameters are crucial for achieving desired performance levels, requiring domain expertise. 2) The decision-making process in DRL models is often opaque, commonly described as a 'black box'. 3) DRL models are data hungry. In response, we propose CP-AgentNet, the first framework to employ generative agents as autonomous decision-makers for communication protocol design. This approach addresses these challenges by creating an autonomous system for protocol design, significantly reducing human effort. As practical use cases, we developed LLMA (LLM-agents-based multiple access) and CPTCP (CP-Agent-based TCP) tailored for heterogeneous environments. Our comprehensive simulations have demonstrated the efficient coexistence of LLMA and CPTCP with nodes using different types of protocols, as well as enhanced explainability.