GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration
This addresses the time-consuming and error-prone process for enterprise network engineers, though it appears incremental by combining existing LLM capabilities with network-specific multimodal tasks.
The paper tackles the problem of automating complex, manual network engineering by introducing GeNet, a multimodal LLM-based co-pilot that interprets and updates network topologies and configurations based on user intents, with evaluation on enterprise scenarios showing accurate topology interpretation and potential effort reduction.
Communication network engineering in enterprise environments is traditionally a complex, time-consuming, and error-prone manual process. Most research on network engineering automation has concentrated on configuration synthesis, often overlooking changes in the physical network topology. This paper introduces GeNet, a multimodal co-pilot for enterprise network engineers. GeNet is a novel framework that leverages a large language model (LLM) to streamline network design workflows. It uses visual and textual modalities to interpret and update network topologies and device configurations based on user intents. GeNet was evaluated on enterprise network scenarios adapted from Cisco certification exercises. Our results demonstrate GeNet's ability to interpret network topology images accurately, potentially reducing network engineers' efforts and accelerating network design processes in enterprise environments. Furthermore, we show the importance of precise topology understanding when handling intents that require modifications to the network's topology.