发表机构
University of Ottawa; University of Bologna（渥太华大学; 博洛尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Intent2Tc利用语言模型和数字孪生、RAG等技术，将业务级流量整形意图自动翻译为可执行的Linux tc配置，在RFC 9315意图上实现高语义保真度与配置准确性。
AI 中文摘要
自动且高度可用的服务质量（QoS）执行需要将高层服务意图翻译为可部署的流量管理策略。尽管基于意图的网络（IBN）已简化了策略规范，但弥合业务级意图与可执行网络配置之间的鸿沟仍然复杂、易错且难以自动化。本文提出Intent2Tc，一个闭环的、由语言模型驱动的框架，将业务级流量整形意图翻译为声明性子意图，进而翻译为经过验证的、可执行的Linux流量控制（tc）配置。该框架集成了基于主动队列管理（AQM）的数字孪生（DT）语义模型、自动化元数据提取、基于批判的优化以及基于检索增强生成（RAG）的知识复用，以提高语义一致性和配置可靠性。我们在100个符合请求评论（RFC）9315标准的流量整形意图上，评估了多个开源大语言模型（LLM）和小语言模型（SLM），以及Claude Sonnet-4.6。在两个翻译阶段中，Intent2Tc均实现了高语义保真度、配置准确性和部署就绪性，其中Claude Sonnet-4.6达到了0.98的语义相似度、1.0的语义单元覆盖率和0.045的归一化编辑距离。此外，RAG减少了令牌消耗和推理延迟，同时使Phi-4-mini等紧凑模型能够接近显著更大模型的性能。Linux tc作为目标配置平台，展示了所提框架的实际适用性。
英文摘要
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.
Comments6 pages, 6 figures, Accepted to IEEE Conference on Future Communications and Networks (FCN) 2026
