Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms

TL;DR

This paper presents an innovative framework leveraging large language models for intelligent log processing and autonomous debugging in cloud AI platforms, significantly enhancing fault localization accuracy and system self-repair capabilities.

Contribution

It introduces a novel LLM-based debugging framework with multi-stage semantic inference, dynamic log structuring, and reinforcement learning-driven decision-making for cloud AI systems.

Findings

Improves fault location accuracy by 16.2%.

Enhances semantic understanding and adaptive debugging.

Supports heterogeneous cloud environments.

Abstract

With the increasing complexity and rapid expansion of the scale of AI systems in cloud platforms, the log data generated during system operation is massive, unstructured, and semantically ambiguous, which brings great challenges to fault location and system self-repair. In order to solve this problem, this paper proposes an intelligent log processing and automatic debugging framework based on Large Language Model (LLM), named Intelligent Debugger (LLM-ID). This method is extended on the basis of the existing pre-trained Transformer model, and integrates a multi-stage semantic inference mechanism to realize the context understanding of system logs and the automatic reconstruction of fault chains. Firstly, the system log is dynamically structured, and the unsupervised clustering and embedding mechanism is used to extract the event template and semantic schema. Subsequently, the fine-tuned LLM combined with the multi-round attention mechanism to perform contextual reasoning on the log sequence to generate potential fault assumptions and root cause paths. Furthermore, this paper introduces a reinforcement learning-based policy-guided recovery planner, which is driven by the remediation strategy generated by LLM to support dynamic decision-making and adaptive debugging in the cloud environment. Compared with the existing rule engine or traditional log analysis system, the proposed model has stronger semantic understanding ability, continuous learning ability and heterogeneous environment adaptability. Experiments on the cloud platform log dataset show that LLM-ID improves the fault location accuracy by 16.2%, which is significantly better than the current mainstream methods