Language models convert business intents into deployable linux traffic controls
Intent2Tc: Automated Intent-to-Traffic Control Translation with Language Models
Networking and Internet ArchitectureArtificial IntelligenceComputation and Language
Summary
Making sure internet traffic works well often needs translating big-picture goals into detailed technical rules, which can be hard and error-prone. The authors created Intent2Tc, a system that uses language models to automatically turn these business-level goals into working Linux traffic control setups. Their method checks and improves configurations with a digital model and reuses knowledge to make the system smarter over time. They tested several language models and showed high accuracy and practical readiness for real-world use.
What this means in practice
- •For network schedulers: Automatically convert business-level traffic priorities into precise Linux configurations to enforce network quality of service efficiently.
- •For cloud infrastructure operators: Generate and validate traffic control rules from operator intents to streamline deployment of network traffic policies in cloud data centers.
- •For internet service providers: Translate customer or business service requirements directly into executable traffic management policies to improve network service quality.$Commercial implications: Enables providers to offer dynamic, intent-driven traffic management products tailored to client needs using an automated translation system.
Authors
Andrea Masini, Sudipta Acharya, Paolo Bellavista, Luca Foschini, Burak Kantarci
Abstract
Automated and highly usable Quality-of-Service (QoS) enforcement requires translating high-level service intents into deployable traffic-management policies. Although intent-based networking (IBN) has simplified policy specification, bridging the gap between business-level intents and executable network configurations remains complex, error-prone, and difficult to automate. This paper presents Intent2Tc, a closed-loop language-model-driven framework that translates business-level traffic-shaping intents into declarative sub-intents and subsequently into validated, executable Linux traffic control (tc) configurations. The framework integrates an Active Queue Management (AQM)-based digital twin (DT) semantic model, automated metadata extraction, critique-driven refinement, and Retrieval-Augmented Generation (RAG)-based knowledge reuse to improve semantic consistency and configuration reliability. We evaluate multiple open-source large language models (LLMs) and small language models (SLMs), together with Claude Sonnet-4.6, on 100 Request for Comments (RFC) 9315-compliant traffic-shaping intents. Across both translation stages, Intent2Tc achieves high semantic fidelity, configuration accuracy, and deployment readiness, with Claude Sonnet-4.6 reaching 0.98 semantic similarity, 1.0 semantic unit coverage, and 0.045 normalized edit distance. Furthermore, RAG reduces token consumption and inference latency while enabling compact models such as Phi-4-mini to approach the performance of substantially larger models. Linux tc serves as the target configuration platform, demonstrating the practical applicability of the proposed framework.