From Metasynthesis to Emergent Engineering: The Development of Xuesen Qian’s Open Complex Giant Systems Thought in the Era of Large Models

In 1990, Mr. Xuesen Qian proposed the concept of “Open Complex Giant Systems” (Open Complex Giant Systems or Open Complex Meta Systems, for simplicity, hereafter referred to as Complex Meta Systems, CMS) and the methodology of “Metasynthesis from Qualitative to Quantitative,” profoundly revealing the essence of a class of systems that can neither be reduced to the sum of simple systems nor grasped solely by qualitative experience. However, due to the lack of computational tools to handle large-scale heterogeneous agent interactions, emergent behaviors, and non-ergodic dynamics at the time, this thought remained at the methodological level for a long time, failing to achieve a systematic construction of theorization, mathematization, and programmization. This paper takes the emergent capabilities of Large Language Models (LLMs) as a technological opportunity to inherit and develop Xuesen Qian’s intellectual legacy. We first reconstruct the modern definition of CMS: a hybrid dynamical system of information-energy-value composed of heterogeneous intelligent agents, characterized by self-organized criticality, non-ergodic dynamics, and stratified emergence. Furthermore, we establish a three-level theoretical framework: at the micro level, formalizing the agent cognitive architecture with information geometry; at the meso level, characterizing group co-evolution with self-organized criticality; and at the macro level, uniformly describing the formal ontology of emergent phenomena with category theory. Finally, we propose the methodological system and programmatic implementation framework of “Emergent Engineering,” upgrading metasynthesis from “human-machine collaborative discussion” to a new cognitive paradigm of “human-AI-environment synergistic emergence.” This paper marks the evolution of Xuesen Qian’s complex giant systems thought from the three-stage progression of “qualitative holism—quantitative reductionism—qualitative-to-quantitative metasynthesis” to the five-stage closed loop of “qualitative hypothesis generation—quantitative modeling and computation—LLM emergent verification—causal mechanism extraction—theoretical iterative updating,” providing a new mathematical foundation and computational platform for complex systems research.