Research map / Large language models / AI and society

Towards Autonomous Network Management: AI-Driven Framework for Intelligent Log Analysis, Troubleshooting and Documentation

AAAI 2025 · Large language models › AI and society · approach: Social-science view of AI evaluation

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Doctoral-symposium proposal for an LLM plus RAG multi-agent framework with human-in-the-loop validation that automates network log analysis, troubleshooting recommendations, and documentation generation.

Problem

Network administrators struggle with large volumes of heterogeneous log data, making log analysis, troubleshooting, and documentation error-prone and labor-intensive; existing tools need proprietary query languages and manual event correlation.

Approach

A closed-loop, human-assisted framework of three RAG-based LLM agents (Log Analyst, Troubleshooting Recommender, Documenter) with a human validator, where generated documents feed back into the RAG knowledge base so agents can use past issues and solutions.

Key results

• No quantitative results are reported; the paper describes a planned evaluation using precision, recall, F1-score and user feedback.
• Preliminary LangChain-based implementation handles PDF, text, and JSON ingestion, chunking, embedding, and vector-index retrieval as of September 2024.

Limitations

• No experimental results; the framework is a proposal with only a preliminary implementation.
• Evaluation and real-world deployment are planned but not yet performed.
• Specific LLMs, datasets, and benchmarks are not named.

Experimental setup

Datasets: network device logs historical network issue records best-practice documentation

Metrics: precision recall F1-score acceptance/modification rate of recommendations

Builds on: Retrieval-Augmented Generation ReAct LangChain

Closest papers by meaning

• RoutingBench: Can Agentic Routing Analysis Scale to Production Datacenter Networks? (NeurIPS 2026 · similarity 0.82)
• JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG (ICML 2026 · similarity 0.81)
• OWL: A Large Language Model for IT Operations (ICLR 2024 · similarity 0.81)
• SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery (NeurIPS 2026 · similarity 0.81)
• AI-Researcher: Autonomous Scientific Innovation (NeurIPS 2025 · similarity 0.81)
• MARS: Modular Agent with Reflective Search for Automated AI Research (ICML 2026 · similarity 0.81)