发表机构
Emory University; University of Illinois Urbana-Champaign（埃默里大学; 伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出动作条件化的网络世界模型，作为复杂系统算法设计中的快速评估器，使编码代理设计的算法在多数设置中超越基线，并显著加速模拟。
AI 中文摘要
世界模型通过模拟环境并预测其在动作下的变化，越来越多地被应用于机器人技术等现实世界场景。复杂系统同样需要这种工具，因为动作的效果并非即时显现。例如，为宣传活动选择种子节点，或为流行病接种免疫节点，单独来看变化甚微；关键在于后续步骤中逐步展开的结果。设计一种算法以选择此类动作来最大化任务预期性能，本质上是迭代的，每个候选方案都必须根据其产生的结果进行评分。获取该结果一直依赖于模拟，当候选方案在众多采样轨迹上进行评估时，模拟成本便成为瓶颈。我们提出了一种动作条件化的网络世界模型，该模型学习网络在随时间干预下的扩散动态，将每个动作应用于网络，并预测随之而来的结果。它作为算法设计循环中的快速评估器，在该循环中，编码代理利用完整展开、动作级信用以及针对替代干预的反事实探测的反馈来设计和改进可执行算法。在八个网络任务和五种扩散模型上，所设计的算法在141种设置中的138种中达到或超过了最强报告的基线，同时使得展开速度比蒙特卡洛模拟快达14.5倍。代码将在接受后发布。
英文摘要
World models, which simulate an environment and predict how it changes under actions, are increasingly used in real-world applications such as robotics. Complex systems call for the same tool because the effect of an action is not immediate. Seeding nodes for a campaign, or immunizing nodes against an epidemic, changes little on its own; what matters is the outcome that unfolds over the steps that follow. Designing an algorithm that selects such actions to maximize expected performance on a task is inherently iterative, and every candidate must be scored by the outcome it produces. Obtaining that outcome has relied on simulation, whose cost becomes a bottleneck when candidates are evaluated over many sampled trajectories. We propose an action-conditioned Network World Model that learns a network's diffusion dynamics under interventions over time, applies each action to the network, and predicts the outcome that follows. It serves as a fast evaluator inside an algorithm design loop in which a coding agent designs and refines executable algorithms using feedback from full rollouts, action-level credit, and counterfactual probes over alternative interventions. Across eight network tasks and five diffusion models, the designed algorithms match or exceed the strongest reported baseline in 138 of 141 settings while enabling up to 14.5 times faster rollouts than Monte Carlo simulation. Code will be released upon acceptance.
Comments46 pages, 7 figures, 17 tables. Preprint
