PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis

• URL: http://arxiv.org/abs/2606.00582v1
• Date: Sat, 30 May 2026 07:18:42 GMT
• Title: PropLLM: Propagation-Aware Scene Reconstruction for Network Fault Diagnosis
• Abstract summary: This paper proposes PropLLM, which is the first to integrate the hop-by-hop scene reconstruction paradigm with the generative reasoning capabilities of LLMs.<n>On a real-world Wi-Fi multimodal fault dataset, PropLLM improves fault type diagnosis accuracy by 3.9% and root cause localization accuracy by 4.7%.
• Score: 13.502332249072696
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Network faults propagate layer by layer along topology and protocol dependencies, yet operations systems typically observe only symptomatic alerts at the tail end of propagation chains, where distinct root-cause faults may produce highly similar end-point symptoms. Existing approaches, whether rule-based, machine learning (ML)-based, or large language model (LLM)-based, fundamentally map the alert set to a diagnosis in a single pass and are structurally incapable of resolving this end-point ambiguity. This paper proposes PropLLM, which is the first to integrate the hop-by-hop scene reconstruction paradigm with the generative reasoning capabilities of LLMs. Starting from end-point alerts, PropLLM traces back hop-by-hop along the propagation path, retrieving verifiable factual evidence from a dual-layer knowledge graph (KG) at each hop, while the proposed Temporal Causal Propagation Attention (TCPA) mechanism encodes known topological causal priors directly into the attention computation to guide the model along the correct causal direction, ultimately localizing the root cause and determining the fault type through a fully evidenced causal chain. On a real-world Wi-Fi multimodal fault dataset, PropLLM improves fault type diagnosis accuracy by 3.9\% and root cause localization accuracy by 4.7\% over the strongest baseline, while reducing the hallucination rate by 50.8\%. Supplementary experiments on the TeleLogs 5G dataset further demonstrate the effectiveness of the proposed method across different network scenarios.

Related papers

• DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems [61.11435469308521]
  We propose DCFA, a training-free framework for failure attribution in large language model systems.<n> DCFA integrates a global module that constructs structured causal-inspired dependency graphs from system traces.<n>Experiments show that DCFA improves step-level accuracy by up to 8.27% over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-09-04T05:29:31Z)
• How Far Can Root Cause Analysis Go on Real-World Telemetry Data? [0.8594140167290097]
  We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes.<n>We present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines.
  arXiv  Detail & Related papers  (2026-07-15T07:54:46Z)
• SCOPE: A Syndrome-Driven Control Plane for QEC-Enabled Quantum Networks [7.746657732894142]
  We present SCOPE, a network-layer architecture that enables joint routing and coding optimization using purely passive telemetry.<n>SCOPE reduces estimation error by more than 60% relative to a standard EM baseline.<n>In large-scale networks, this precision reduces logical error rates by 30-35% (up to 65%) against topology-aware baselines.
  arXiv  Detail & Related papers  (2026-06-07T23:00:09Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices [10.602349579405832]
  Root cause analysis (RCA) intricmetrics is challenging due to noisy and heterogeneous multimodal observability.<n>Recent LLM-based RCA agents can generate tool-grounded explanations, yet they often remain topology-agnostic.<n>We propose textbfTopoEvo, a topology-aware self-evolving multi-agent that couples graph representation learning with structured, topology-constrained reasoning.
  arXiv  Detail & Related papers  (2026-05-15T04:45:44Z)
• Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign [11.440086398117318]
  Peak-Detector is a novel framework for robust, cross-modal, and explainable peak detection.<n>A core innovation is a "peak-modal" technique that transforms time-series data into a condensed format.<n>Peak-Detector demonstrates strong cross-representation performance across four modalities.
  arXiv  Detail & Related papers  (2026-05-15T04:08:00Z)
• HiFiNet: Hierarchical Fault Identification in Wireless Sensor Networks via Edge-Based Classification and Graph Aggregation [11.108171977551619]
  HiFiNet is a hierarchical fault identification framework for wireless networks.<n>It produces more accurate predictions by capturing both local temporal patterns and network-wide spatial dependencies.<n>It significantly outperforms existing methods in accuracy, F1-score, and precision.
  arXiv  Detail & Related papers  (2025-11-06T16:15:19Z)
• Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction [58.51530390018909]
  Large Language Model based multi-agent systems excel at collaborative problem solving but remain brittle to cascading errors.<n>We present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction.
  arXiv  Detail & Related papers  (2025-10-16T05:35:37Z)
• MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model Agents [12.160412894251406]
  MicroRCA-Agent is an innovative solution for microservice root cause analysis based on large language model agents.<n>The proposed solution demonstrates superior performance in complex microservice fault scenarios, achieving a final score of 50.71.
  arXiv  Detail & Related papers  (2025-09-19T05:57:03Z)
• FaultExplainer: Leveraging Large Language Models for Interpretable Fault Detection and Diagnosis [7.161558367924948]
  This paper presents FaultExplainer, an interactive tool designed to improve fault detection, diagnosis, and explanation in the Tennessee Eastman Process (TEP)<n>FaultExplainer integrates real-time sensor data visualization, Principal Component Analysis (PCA)-based fault detection, and identification of top contributing variables within an interactive user interface powered by large language models (LLMs)<n>We evaluate the LLMs' reasoning capabilities in two scenarios: one where historical root causes are provided, and one where they are not to mimic the challenge of previously unseen faults.
  arXiv  Detail & Related papers  (2024-12-19T03:35:06Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
  We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
  arXiv  Detail & Related papers  (2023-08-06T05:58:45Z)
• Disentangled Causal Graph Learning for Online Unsupervised Root Cause Analysis [49.910053255238566]
  Root cause analysis (RCA) can identify the root causes of system faults/failures by analyzing system monitoring data. Previous research has mostly focused on developing offline RCA algorithms, which often require manually initiating the RCA process. We propose CORAL, a novel online RCA framework that can automatically trigger the RCA process and incrementally update the RCA model.
  arXiv  Detail & Related papers  (2023-05-18T01:27:48Z)

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.