Title: Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents

Authors: Fujiang Yuan; Xia Huang; Lusheng Wang; Jun Ding; Zhen Tian; Yuxin Wang; Shaojie Gu; Yuki Funabora; Yanhong Peng; Zebing Mao

Addresses: College of Mechanical Engineering, Chongqing University of Technology, Chongqing, 400054, China ' College of Mechanical Engineering, Chongqing University of Technology, Chongqing, 400054, China ' College of Mechanical Engineering, Chongqing University of Technology, Chongqing, 400054, China ' College of Mechanical Engineering, Chongqing University of Technology, Chongqing, 400054, China ' James Watt School of Engineering, University of Glasgow, G12 8QQ, UK ' School of Energy and Power, Jiangsu University of Science and Technology, Zhenjiang, 212100, China ' Magnesium Research Center, Kumamoto University, Kumamoto, 860-8555, Japan ' Department of Information and Communication Engineering, Nagoya University, Nagoya, 4648601, Japan ' College of Mechanical Engineering, Chongqing University of Technology, Chongqing, 400054, China; Department of Information and Communication Engineering, Nagoya University, Nagoya, 4648601, Japan ' State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou, 310027, China

Abstract: 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.

Keywords: embodied intelligence; large language model; LLM; knowledge base; reasoning ability; general embodied intelligence; GEI.

DOI: 10.1504/IJHM.2026.154223

International Journal of Hydromechatronics, 2026 Vol.9 No.2, pp.250 - 316

Received: 08 Jul 2025
Accepted: 03 Sep 2025
Published online: 17 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article