从观察到洞察：机制世界模型与自主发现探索

中文摘要 AI 辅助

基础模型的最新进展改变了科学领域的人工智能，在从蛋白质折叠到天气预报等领域实现了非常准确的预测性能。然而，仅预测并不构成科学发现。科学理解依赖于揭示产生观测结果的可重复使用的解释机制，而当代机器学习仍主要围绕预测映射而非解释结构组织。本文认为科学发现本质上是一个知识组织问题。为此，我们引入机制世界模型，这是一种新的设计范式，将可重复使用的机制置于表示、计算和学习的中心。借鉴科学哲学的见解，我们推导发现所需的计算能力……最后，我们展示了包括机制可解释性、因果表示学习、方程发现和模块化架构等不同研究方向如何捕捉该范式的互补要素，但缺乏统一框架。我们提出机制世界模型作为将人工智能从预测性预测转向自主科学发现的概念基础和计算蓝图。

英文摘要

Recent advances in foundation models have transformed AI for Science, enabling remarkably accurate predictive performance across domains ranging from protein folding to weather forecasting. Yet prediction alone does not constitute scientific discovery. Scientific understanding depends on uncovering the reusable explanatory mechanisms that generate observations, whereas contemporary machine learning remains fundamentally organised around predictive mappings rather than explanatory structure. In this paper, we argue that scientific discovery is fundamentally a problem of knowledge organisation. To this end, we introduce Mechanistic World Models, a new design paradigm that places reusable mechanisms at the centre of representation, computation and learning. Drawing on insights from the philosophy of science, we derive the computational capabilities required for discovery, identify the design principles and inductive pressures that encourage explanatory knowledge to emerge, and formalise the anatomy of a mechanism-centric world model. Finally, we show how diverse research directions including mechanistic interpretability, causal representation learning, equation discovery and modular architectures capture complementary ingredients of this paradigm while lacking a unified framework. We propose Mechanistic World Models as a conceptual foundation and computational blueprint for moving AI beyond predictive forecasting towards autonomous scientific discovery.

发表机构

• MPI for Intelligent Systems & ELLIS Institute（马克斯·普朗克智能系统研究所及埃利斯研究所）

机构由 AI 辅助整理，请以论文原文为准。