Towards an Agentic Workflow for Internet Measurement Research

2025-11-13

AI Summary

Internet measurement research suffers from an accessibility crisis due to tool fragmentation and high domain expertise requirements—especially during sudden network outages, where manually constructing diagnostic workflows (e.g., topology discovery, routing analysis, dependency modeling) is time-consuming and heavily reliant on expert knowledge. This paper introduces ArachNet, the first LLM-based agent system that automatically generates expert-level measurement workflows. Methodologically, it employs a novel four-role collaborative agent architecture enabling problem decomposition, tool orchestration, multi-framework integration, and closed-loop reasoning. Its key contribution lies in empirically uncovering and formalizing compositional regularities in measurement expertise—demonstrating their automation feasibility for the first time. Experiments show that ArachNet-generated workflows match expert quality, reducing complex analyses from days to minutes, thereby significantly improving diagnostic efficiency, reproducibility, and accessibility across the networking research community.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Web Mining and Content Analysis: Web measurements
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Internet measurement research faces an accessibility crisis: complex analyses require custom integration of multiple specialized tools that demands specialized domain expertise. When network disruptions occur, operators need rapid diagnostic workflows spanning infrastructure mapping, routing analysis, and dependency modeling. However, developing these workflows requires specialized knowledge and significant manual effort. We present ArachNet, the first system demonstrating that LLM agents can independently generate measurement workflows that mimics expert reasoning. Our core insight is that measurement expertise follows predictable compositional patterns that can be systematically automated. ArachNet operates through four specialized agents that mirror expert workflow, from problem decomposition to solution implementation. We validate ArachNet with progressively challenging Internet resilience scenarios. The system independently generates workflows that match expert-level reasoning and produce analytical outputs similar to specialist solutions. Generated workflows handle complex multi-framework integration that traditionally requires days of manual coordination. ArachNet lowers barriers to measurement workflow composition by automating the systematic reasoning process that experts use, enabling broader access to sophisticated measurement capabilities while maintaining the technical rigor required for research-quality analysis.

Problem

• Automating complex internet measurement workflows requiring specialized expertise
• Reducing manual effort in diagnostic analysis during network disruptions
• Lowering barriers to sophisticated measurement capabilities for non-experts

Innovation

• LLM agents automate expert measurement workflow generation
• Specialized agents mirror expert problem decomposition process
• Automated multi-framework integration replaces manual coordination