用游戏化框架让机器自主推翻旧理论，发现新规律
Newton to Einstein: Axiom-Based Discovery via Game Design
- 将科学探索设计成规则可演化的游戏，智能体通过改写公理来解释异常现象
- 在逻辑类游戏中验证了系统能自发演化出新公理，解决原问题无法求解的难题
- 适合追求可解释性与理论创新的科研人员，推动机器从模仿到创造
本文主张机器学习在科学发现中的范式应从归纳模式识别转向基于公理的推理。我们提出一种游戏设计框架，将科学探究重构为规则演化系统：智能体在公理约束的环境中运行，并通过修改公理来解释异常观测。与传统依赖固定假设的机器学习方法不同，该方法允许通过系统性规则调整发现新的理论结构。初步实验在基于逻辑的游戏环境中验证了其可行性，显示智能体能够演化出解决先前不可解问题的新公理。该框架为构建具备创造力、可解释性与理论驱动能力的机器学习系统奠定了基础。
原文摘要 · Abstract (English)
This position paper argues that machine learning for scientific discovery should shift from inductive pattern recognition to axiom-based reasoning. We propose a game design framework in which scientific inquiry is recast as a rule-evolving system: agents operate within environments governed by axioms and modify them to explain outlier observations. Unlike conventional ML approaches that operate within fixed assumptions, our method enables the discovery of new theoretical structures through systematic rule adaptation. We demonstrate the feasibility of this approach through preliminary experiments in logic-based games, showing that agents can evolve axioms that solve previously unsolvable problems. This framework offers a foundation for building machine learning systems capable of creative, interpretable, and theory-driven discovery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。