企业系统需要学习世界模型吗？上下文对于推断动态的重要性

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

May 12, 2026

作者: Jishnu Sethumadhavan Nair, Patrice Bechard, Rishabh Maheshwary, Surajit Dasgupta, Sravan Ramachandran, Aakash Bhagat, Shruthan Radhakrishna, Pulkit Pattnaik, Johan Obando-Ceron, Shiva Krishna Reddy Malay, Sagar Davasam, Seganrasan Subramanian, Vipul Mittal, Sridhar Krishna Nemala, Christopher Pal, Srinivas Sunkara, Sai Rajeswar

cs.AI

摘要

世界模型使智能体能够通过内化环境动态来预测其行动的效果。然而，在企业系统中，这些动态往往由租户特有的业务逻辑定义，这些逻辑在不同部署中各不相同且随时间演变，导致基于历史转换训练的模型在部署漂移下变得脆弱。我们提出了世界模型文献尚未解决的一个问题：当规则可以在推理时读取时，智能体是否仍需学习它们？我们论证并通过实验证明，在转换动态可配置且可读取的环境中，运行时发现通过将预测锚定到当前系统实例，能够补充离线训练的效果。我们提出了企业发现代理，它们通过读取系统配置而非仅依赖内化表征，在运行时恢复相关的转换动态。我们引入了CascadeBench，一个面向推理的企业级级联预测基准，该基准采用World of Workflows的评估方法，基于多样化的合成环境，并结合部署漂移评估表明：离线训练的世界模型在分布内表现良好，但随着动态变化而性能下降，而基于发现的代理通过将预测锚定到当前实例，在漂移下更具鲁棒性。我们的发现表明，在可配置的企业环境中，智能体不应仅依赖固定的内化动态，而应结合运行时发现相关转换逻辑的机制。

English

World models enable agents to anticipate the effects of their actions by internalizing environment dynamics. In enterprise systems, however, these dynamics are often defined by tenant-specific business logic that varies across deployments and evolves over time, making models trained on historical transitions brittle under deployment shift. We ask a question the world-models literature has not addressed: when the rules can be read at inference time, does an agent still need to learn them? We argue, and demonstrate empirically, that in settings where transition dynamics are configurable and readable, runtime discovery complements offline training by grounding predictions in the active system instance. We propose enterprise discovery agents, which recover relevant transition dynamics at runtime by reading the system's configuration rather than relying solely on internalized representations. We introduce CascadeBench, a reasoning-focused benchmark for enterprise cascade prediction that adopts the evaluation methodology of World of Workflows on diverse synthetic environments, and use it together with deployment-shift evaluation to show that offline-trained world models can perform well in-distribution but degrade as dynamics change, whereas discovery-based agents are more robust under shift by grounding their predictions in the current instance. Our findings suggest that, in configurable enterprise environments, agents should not rely solely on fixed internalized dynamics, but should incorporate mechanisms for discovering relevant transition logic at runtime.