发表机构
College of Mechanical Engineering, Chongqing University of Technology; James Watt School of Engineering, University of Glasgow; School of Energy and Power, Jiangsu University of Science and Technology; Magnesium Research Center, Kumamoto University; Department of Information and Communication Engineering, Nagoya University; State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University（重庆理工大学机械工程学院; 格拉斯哥大学詹姆斯·瓦特工程学院; 江苏科技大学能源与动力学院; 熊本大学镁研究中心; 名古屋大学信息与通信工程系; 浙江大学流体动力与机电系统国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文综述以LLM为核心的智能系统演进，提出整合LLMs、KBs、RA与具身性的概念框架，明确高效LLM部署等五大挑战，为开发复杂动态环境下的自适应多模态智能体提供路线图。
AI 中文摘要
大语言模型（LLMs）、结构化知识库（KBs）与推理能力（RA）的融合，为通用具身智能（GEI）提供了极具前景的发展方向。本文回顾了以LLM为核心的智能系统的演进，重点强调其与知识表示、逻辑推理及物理具身的整合。我们分析了LLM架构、预训练方法、推理机制，以及它们与外部知识源和结构化推理框架的交互。此外，我们研究了智能体在物理环境中学习与行动的具身智能（EI）范式。为整合这些维度，我们提出了一个概念框架，阐明LLMs、KBs、RA与具身性之间的协同作用，该框架作为感知、推理与行动的指导模型，而非已实现的工程架构。为推进向GEI的发展，我们明确了五大关键挑战：高效LLM部署、闭环知识整合、混合符号-神经推理、感知-行动接地及持续学习。本综述为开发能在复杂动态环境中运行的自适应多模态智能体提供了全面路线图。
英文摘要
The convergence of large language models (LLMs), structured knowledge bases (KBs), and reasoning ability (RA) presents a promising trajectory toward general embodied intelligence (GEI). This paper reviews the evolution of LLM-centered intelligent systems, emphasising their integration with knowledge representation, logical reasoning, and physical embodiment. We analyse LLM architectures, pre-training methods, and inference mechanisms, along with their interaction with external knowledge sources and structured reasoning frameworks. Furthermore, we examine embodied intelligence (EI) paradigms wherein agents learn and act in physical environments. To synthesise these dimensions, we present a conceptual framework that illustrates the synergy among LLMs, KBs, RA, and embodiment, serving as a guiding model for perception, reasoning, and action rather than an implemented engineering architecture. To advance toward GEI, we identify five key challenges: efficient LLM deployment, closed-loop knowledge integration, hybrid symbolic-neural reasoning, perception-action grounding, and continual learning. This survey provides a comprehensive roadmap for developing adaptive, multimodal agents capable of operating in complex, dynamic settings.
Journal refInternational Journal of Hydromechatronics 9(2) (2026) 250-316
