做图组合优化或RL求解NP-hard问题的研究者，这篇论文解决了泛化差和扩展性瓶颈，16倍加速和40%泛化提升值得一试，开源库还能直接复用。
图组合优化（GCO）问题因NP难特性而难以精确求解，现有基于强化学习（RL）和图神经网络（GNN）的方法在泛化性和计算可扩展性上存在局限。本文提出Projection Agents，直接在连续GNN动作嵌入空间中预测潜在动作，并通过单次前向传播解码为有效离散动作，避免了传统逐步搜索的开销。该方法在多个基准上实现最高16.2倍推理加速和40%更好的泛化性能，尤其适用于超线性决策空间。同时，作者开源了LaGCO-RL库，支持自动构建潜在动作空间并兼容现有RL-GCO方案，便于复现和适配新问题。
Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization
Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinatorial explosion renders exact methods computationally intractable. Recent advances in Reinforcement Learning (RL) combined with Graph Neural Networks (GNNs) have significantly improved learning-based GCO solvers. However, existing approaches face limitations in both generalization across diverse graph instances and computational scalability as action spaces grow. To address both challenges, we introduce projection agents, a novel RL-GCO approach that operates directly in a continuous GNN-based action embedding space, predicting a desired latent action in a single forward pass and subsequently decoding it into a valid discrete action. Additionally, we enable fair comparison across RL methods through a shared embedding space for both observations and actions. Across diverse benchmarks, our approach achieves up to 16.2x faster inference and up to 40% better generalization than existing solutions using only simple nearest-neighbor decoding, while opening the door to strong RL performance in super-linear decision spaces with multiple interdependent variables. Finally, we release LaGCO-RL, a Python library that automates latent action-space construction and supports existing RL-GCO solutions, promoting reproducibility and adaptation to new GCO benchmarks.