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

• URL: http://arxiv.org/abs/2603.00569v1
• Date: Sat, 28 Feb 2026 09:36:48 GMT
• Title: TopoEdge: Topology-Grounded Agentic Framework for Edge Networking Code Generation and Repair
• Authors: Haomin Qi, Bohan Liu, Zihan Dai, Yunkai Gao,
• Abstract summary: TopoEdge is a framework for software-defined networking (SDN) configuration generation and repair.<n>TopoEdge represents each target topology as a router-level graph and embeds it using a contrastively trained graph neural network (GNN)<n>The target topology, retrieved reference topology, and reference driver are assembled into a topology-grounded retrieval-augmented generation context (TopoRAG)
• Score: 1.8860840010379987
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• ANCHOR: Branch-Point Data Generation for GUI Agents [52.22377425487]
  End-to-end GUI agents for real desktop environments require large amounts of high-quality interaction data.<n>We present a trajectory expansion framework Anchor that bootstraps scalable desktop supervision from a small set of verified seed demonstrations.<n>Experiments on standard desktop benchmarks, OSWorld and WindowsAgentArena, show that models fine-tuned on our expanded corpus achieve consistent improvements.
  arXiv  Detail & Related papers  (2026-02-06T19:55:26Z)
• Single-Edge Node Injection Threats to GNN-Based Security Monitoring in Industrial Graph Systems [2.405577583760006]
  Graph neural networks (GNNs) are increasingly adopted in industrial graph-based monitoring systems.<n> adversary that compromises a small number of edge devices may inject counterfeit nodes to bias downstream decisions.<n>This paper formulates deployment-oriented node-injection attacks under constrained resources and proposes the emphSingle-Edge Graph Injection Attack (SEGIA)
  arXiv  Detail & Related papers  (2026-02-01T09:19:54Z)
• BGPFuzz: Automated Configuration Fuzzing of the Border Gateway Protocol [3.0013352260516744]
  Misconfigurations in Border Gateway Protocol (BGP) can lead to severe outages and security breaches.<n>We present BGPFuzz, a structure-aware and stateful fuzzing framework that systematically mutates BGP configurations and evaluates their effects in network.
  arXiv  Detail & Related papers  (2025-12-05T01:53:14Z)
• AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices [5.081228499547384]
  We introduce AegisMCP, a protocol-level intrusion detector.<n>AegisMCP achieves sub-second per-window model inference and end-to-end alerting.
  arXiv  Detail & Related papers  (2025-10-22T10:50:22Z)
• Repairing Networks of $\mathcal{EL_\perp}$ Ontologies using Weakening and Completing -- Extended version [4.287175019018556]
  We propose a framework for repairing ontology networks that deals with this issue. It defines basic operations such as weakening and completing. We show the influence of the combination operators on the quality of the repaired network and present an implemented tool.
  arXiv  Detail & Related papers  (2024-07-26T16:15:33Z)
• Refined Edge Usage of Graph Neural Networks for Edge Prediction [51.06557652109059]
  We propose a novel edge prediction paradigm named Edge-aware Message PassIng neuRal nEtworks (EMPIRE) We first introduce an edge splitting technique to specify use of each edge where each edge is solely used as either the topology or the supervision. In order to emphasize the differences between pairs connected by supervision edges and pairs unconnected, we further weight the messages to highlight the relative ones that can reflect the differences.
  arXiv  Detail & Related papers  (2022-12-25T23:19:56Z)
• Towards AIOps in Edge Computing Environments [60.27785717687999]
  This paper describes the system design of an AIOps platform which is applicable in heterogeneous, distributed environments. It is feasible to collect metrics with a high frequency and simultaneously run specific anomaly detection algorithms directly on edge devices.
  arXiv  Detail & Related papers  (2021-02-12T09:33:00Z)
• Geometry Constrained Weakly Supervised Object Localization [55.17224813345206]
  We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization. The detector predicts the object location defined by a set of coefficients describing a geometric shape. The generator takes the resulting masked images as input and performs two complementary classification tasks for the object and background. In contrast to previous approaches, GC-Net is trained end-to-end and predict object location without any post-processing.
  arXiv  Detail & Related papers  (2020-07-19T17:33:42Z)
• End-to-End Object Detection with Transformers [88.06357745922716]
  We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components. The main ingredients of the new framework, called DEtection TRansformer or DETR, are a set-based global loss.
  arXiv  Detail & Related papers  (2020-05-26T17:06:38Z)
• DHP: Differentiable Meta Pruning via HyperNetworks [158.69345612783198]
  This paper introduces a differentiable pruning method via hypernetworks for automatic network pruning. Latent vectors control the output channels of the convolutional layers in the backbone network and act as a handle for the pruning of the layers. Experiments are conducted on various networks for image classification, single image super-resolution, and denoising.
  arXiv  Detail & Related papers  (2020-03-30T17:59:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.