Towards an Agentic Workflow for Internet Measurement Research

TL;DR

ArachNet addresses the accessibility barrier in Internet measurement by automating end-to-end workflow composition through a four-agent architecture that mirrors expert reasoning: problem analysis (QueryMind), solution design (WorkflowScout), implementation (SolutionWeaver), and registry evolution (RegistryCurator). The system relies on a curated Measurement Capability Registry to unify diverse measurement tools and supports expert oversight in an expert mode. Through progressively challenging case studies in Internet resilience and forensic analysis, ArachNet demonstrates expert-level reasoning, multi-framework orchestration, and robust temporal analysis while reducing development effort from days to hundreds of lines of code. This approach promises broader access to sophisticated measurement capabilities while maintaining research-grade rigor, with open-source prompts and case studies to foster adoption and further evaluation.

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.

Figures (1)

• Figure 1: ArachNet design with four specialized agents. QueryMind analyzes and decomposes problems, WorkflowScout explores and designs solution workflows, SolutionWeaver implements executable workflows, and RegistryCurator evolves ArachNet's capabilities.