Result reproduction of computer networking research is challenging as the scarcity of open-source implementations and the complexity of heterogeneous system architectures. Even though Large Language Models have demonstrated potential in code generation, existing code generation frameworks often fail to address the long-context constraints and intricate logical dependencies, which are vital in reproducing network systems from academic papers. Thus, we introduce RepLLM, an end-to-end multi-agent framework designed to automate code reproduction from paper content. RepLLM features a collaborative architecture comprising four specialized agents—Content Parsing, Architecture Design, Code Generation, and Audit & Repair, which are coordinated through Shared Memory mechanism to ensure global context consistency. With the enhancement of Structured Chain-of-Thought LLM reasoning and a sandbox-isolated static-dynamic debugging methodology, our framework effectively resolves semantic discrepancies and runtime errors, thereby improving reliable reproductions. Extensive evaluations on representative papers in top conferences demonstrate that RepLLM outperforms state-of-the-art system-level LLM frameworks in generating compile-ready and logically correct systems. Our results show that, with the aid of RepLLM, we can reproduce 95% of the original benchmarks within approximately two hours while reducing token consumption by up to 10% compared with state-of-the-art baselines.

Traffic engineering (TE) is widely used to optimize network performance in modern networks. Typically, TE is formulated as a multiple-commodity flow (MCF) optimization problem and solved using mathematical solvers or machine learning approaches, but it becomes unscalable as the network size grows. Existing methods often limit available paths for flow allocation to speed up problem-solving, but this compromises TE performance. Achieving both high performance and fast decisionmaking with free path selection remains a significant challenge. This paper proposes TELD, a scalable and high-performance TE framework with free path selection. TELD leverages Graph Neural Networks (GNNs) that are widely proven with high efficiency in capturing network-specific characteristics and enabling faster decision-making than mathematical solvers. Our key idea is to reformulate the MCF problem into a learningfriendly representation and integrate TE constraints directly into GNN training and inference. The key challenge here is how to efficiently combine the problem reformulation with GNN. TELD tackles this with two critical designs. First, observing that GNNs work better with continuous features, TELD relaxes the freepath MCF formulation by treating flow allocation variables as continuous rather than discrete. Second, TELD introduces a multi-constraint hybrid GNN and a result fine-tuning mechanism to further improve GNN efficiency in TE. Extensive experiments show that TELD outperforms the state-of-the-art GNN-based TE framework by$\sim 55\%$and reduces decision latency by three orders of magnitude compared to mathematical solvers.

Learn to Optimize (L2O) trains deep neural network-based solvers for optimization, achieving success in accelerating convex problems and improving non-convex solutions. However, L2O lacks rigorous theoretical backing for its own training convergence, as existing analyses often use unrealistic assumptions-a gap this work highlights empirically. We bridge this gap by proving the training convergence of L2O models that learn Gradient Descent (GD) hyperparameters for quadratic programming, leveraging the Neural Tangent Kernel (NTK) theory. We propose a deterministic initialization strategy to support our theoretical results and promote stable training over extended optimization horizons by mitigating gradient explosion. Our L2O framework demonstrates over 50% better optimality than GD and superior robustness over state-of-the-art L2O methods on synthetic datasets. The code of our method can be found from https://github.com/NetX-lab/MathL2OProof-Official.

Learning to optimize (L20) is an emerging technique to solve mathematical optimization problems with learning-based methods. Although with great success in many real-world scenarios such as wireless communications, computer networks, and electronic design, existing L2O works lack theoretical demonstration of their performance and robustness in out-of-distribution (OOD) scenarios. We address this gap by providing comprehensive proofs. First, we prove a sufficient condition for a robust L2O model with ho-mogeneous convergence rates over all In-Distribution (InD) instances. We assume an L2O model achieves robustness for an InD scenario. Based on our proposed methodology of aligning OOD problems to InD problems, we also demonstrate that the L2O model's convergence rate in OOD scenarios will deteriorate by an equation of the L2O model's input features. Moreover, we propose an L2O model with a concise gradient-only feature construction and a novel gradient-based history modeling method. Numerical simulation demonstrates that our proposed model outperforms the state-of-the-art baseline in both InD and OOD scenar-ios and achieves up to 10 × convergence speedup. The code of our method can be found from https://github.com/NetX-lab/GoMathL2O-Official.

Solving the sum rate maximization problem for interference reduction in multi-cell multi-user multiple-input multiple-output (MIMO) wireless communication systems has been investigated for a decade. Several machine learning-assisted methods have been proposed under conventional sum rate maximization frameworks, such as the Weighted Minimum Mean Square Error (WMMSE) framework. However, existing learning-assisted methods suffer from a deficiency in parallelization, and their performance is intrinsically bounded by WMMSE. In contrast, we propose a structural learning-only framework from the abstraction of WMMSE. Our proposed framework increases the solvability of the original MIMO sum rate maximization problem by dimension expansion via a unitary learnable parameter matrix to create an equivalent problem in a higher dimension. We then propose a structural solution updating method to solve the higher dimensional problem, utilizing neural networks to generate the learnable matrix-multiplication parameters. We show that the proposed structural learning framework achieves lower complexity than WMMSE thanks to its parallel implementation. Simulation results under practical communication network settings demonstrate that our proposed learning-only framework achieves up to 98% optimality over state-of-the-art algorithms while providing up to 47× acceleration in various scenarios.