TopoEdge: Topology-Grounded Agentic Framework for Edge Networking Code Generation and Repair

2026-02-28

AI Summary

This work addresses the challenges of configuration fragility and limited adaptability in software-defined networking (SDN) under dynamically changing topologies, particularly in edge environments where stringent requirements for low latency, privacy preservation, and local execution prevail. To this end, the authors propose an end-to-end framework tailored for edge deployment, featuring a novel topology embedding–driven retrieval-augmented generation mechanism (TopoRAG). This framework integrates graph neural networks (GNNs) with a multi-agent collaborative architecture, wherein planner, generator, and verifier agents operate in a closed loop to achieve topology-aware configuration synthesis and localized repair. Experimental results demonstrate that the approach enables highly consistent automatic configuration generation and precise repair under topological dynamics, significantly enhancing the reliability and deployment efficiency of SDN configurations in edge settings.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

TopoEdge is a topology-grounded, edge-deployable framework for end-to-end software-defined networking (SDN) configuration generation and repair, motivated by the brittleness of configuration artefacts under topology variation and by strict operational constraints on latency, privacy, and on-site execution. TopoEdge represents each target topology as a router-level graph and embeds it using a contrastively trained graph neural network (GNN), enabling nearest-neighbour retrieval of a verified reference configuration paired with an executable Python driver (a Topotest/pytest test script that orchestrates the emulated network and checks protocol assertions). The target topology, retrieved reference topology, and reference driver are assembled into a topology-grounded retrieval-augmented generation context (TopoRAG), which grounds a distributed, execution-centric generate--verify--repair loop coordinated by a central controller and realised by three role-specialised agents: (i) a Planning agent that produces a topology-consistent configuration plan and a per-device skeleton; (ii) a Generation agent that materialises executable configuration artefacts, including device configurations and the driver; and (iii) a Verification agent that runs the FRRouting Topotest/pytest harness, compresses failures into a compact trace, and emits localised patch directives for iterative repair.

Problem

• edge networking
• SDN configuration
• topology variation
• configuration repair
• operational constraints

Innovation

• topology-grounded
• graph neural network
• retrieval-augmented generation
• agentic framework
• edge networking