发表机构
Zyllion Data Technology (Shanghai) Co.,Ltd.（上海智联数据科技有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出物理AI能力形成的七个非排他性来源框架，通过重构归纳和理论饱和验证，区分能力相似性与形成相似性，支持解释、迁移、复制及治理分析。
AI 中文摘要
与物理AI相关的能力可能源于本质上不同的形成历史，然而现有的按形态、架构、学习算法、任务或领域组织的分类法并未直接回答是什么导致了能力的形成。我们将能力形成来源定义为对能力形成有实质性贡献的因素，区别于组件或构建步骤。我们识别出七个非排他性的来源：记录经验（RE）、预测建模（PM）、评估交互（EI）、替代环境（SE）、机制基础（MG）、具身耦合（EC）和进化驱动（ED）形成。通过理论饱和的重构归纳法，我们将研究矩阵追溯至原始研究，对文献进行去重，设定编码规则，并进行了三轮最大差异和否定案例抽样。挑战包括课程学习和自监督学习、主动推理、开放性和发展性学习、规划与搜索、神经符号架构、数字孪生、生成式物理世界模型以及形态-控制协同设计。在截至2026年9月4日固定的范围和标准内，所有49条证据记录均可由这七个来源单独或组合解释。没有R1-R3挑战产生不可约的第八个来源，R3也不需要新的核心定义或实质性边界规则。因此，我们声称在所述范围内达到理论饱和，而非逻辑完备性或未来全面覆盖。该框架区分了观察到的能力的相似性与形成方式的相似性，支持对解释、迁移、复制、依赖关系、治理证据和地缘经济基础的分析。
英文摘要
Capabilities relevant to Physical AI can arise from materially different formation histories, yet existing taxonomies organized by morphology, architecture, learning algorithm, task, or domain do not directly answer what gives rise to a capability. We define a capability-formation source as a factor materially contributing to capability formation, distinct from components or construction steps. We identify seven non-exclusive sources: Recorded-Experience (RE), Predictive-Modeling (PM), Evaluative-Interaction (EI), Surrogate-Environment (SE), Mechanism-Grounded (MG), Embodied-Coupling (EC), and Evolution-Driven (ED) Formation. Using reconstructive induction with theoretical saturation, we traced a research matrix to primary studies, deduplicated the literature, set coding rules, and conducted three rounds of maximum-difference and negative-case sampling. Challenges included curriculum and self-supervised learning, active inference, open-ended and developmental learning, planning and search, neuro-symbolic architectures, digital twins, generative physical world models, and morphology-control co-design. Within the scope and criteria fixed as of September 4, 2026, all 49 evidence records were explainable by the seven sources individually or in combination. No R1-R3 challenge produced an irreducible eighth source, and R3 required no new core definition or substantive boundary rule. We therefore claim theoretical saturation within the stated scope, not logical completeness or exhaustive future coverage. The framework distinguishes similarity in observed capability from similarity in how it was formed, supporting analysis of explanation, transfer, replication, dependencies, governance evidence, and geoeconomic foundations.
