LMTE：利用语言模型进行WAN流量工程中的推理
LMTE: Putting the "Reasoning" into WAN Traffic Engineering with Language Models
AI总结：
LMTE利用语言模型进行WAN流量工程，通过高效多模态对齐和轻量级配置生成，实现更高效的流量规划和优化。
摘要：
现代宽域网络（WAN）的快速扩展使流量工程（TE）变得更加具有挑战性，因为传统求解器难以跟上步伐。尽管现有的离线机器学习驱动方法利用深度神经网络（DNN）加速TE优化，但它们通常缺乏对未见过的流量模式或拓扑的充分表达性和泛化能力，限制了其实用性。受大型语言模型（LM）成功的影响，本文首次探讨了它们作为通用流量规划器的潜力。我们的贡献是双方面的：（i）理论上，我们证明预训练LM能够模拟TE背后的顺序决策过程，并且关键的是表现出并行推理能力，使它们适合该任务；（ii）实践中，我们提出了LMTE，一种新的基于LM的TE框架，通过高效的多模态对齐和轻量级配置生成来拥抱这些见解，同时保持模型的原始能力。广泛的实验表明，LMTE在五个数据集上匹配了顶级性能，实现了最高达15%的改进最大链路利用率（MLU），并在各种场景下表现出一致的性能下降，例如在高流量动态和链路故障的情况下，性能下降低于5%。此外，它在传统TE求解器上实现了10到100倍的加速。为了帮助未来的工作，我们的代码库可在https://github.com/Y-debug-sys/LMTE上获得。
英文摘要：
The rapid expansion of modern wide-area networks (WANs) has made traffic engineering (TE) increasingly challenging, as traditional solvers struggle to keep pace. Although existing offline ML-driven approaches accelerate TE optimization with deep neural networks (DNNs), they often lack sufficient expressiveness and generalization on unseen traffic patterns or topologies, limiting their practicality. Inspired by the success of large language models (LMs), for the first time, this paper investigates their potential as general-purpose traffic planners. Our contributions are two-fold: (i) Theoretically, we show that pre-trained LMs can simulate the sequential decision processes underlying TE and, crucially, exhibit parallel reasoning capabilities, making them well-suited for the task; (ii) Practically, we present LMTE, a novel LM-driven TE framework that embraces these insights through efficient multimodal alignment and lightweight configuration generation, all while preserving the model's original abilities. Extensive experiments demonstrate that fold matches top-tier performance on five datasets, achieving up to 15\% better maximum link utilization (MLU) and consistently lower performance degradation across diverse scenarios, e.g., less than 5\% with high traffic dynamics and link failures. Moreover, it achieves 10 to 100 times speedups over traditional TE solvers. To aid future works, our codebase is available at https://github.com/Y-debug-sys/LMTE.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
