具身开发者社区

外观

论文arXiv 2608.197942 个月前

迈向通用具身智能：整合大型语言模型、知识库和推理能力以构建下一代AI智能体 ​

本文综述LLM、知识库与推理能力如何融合迈向GEI，提出概念框架并梳理具身智能范式与关键挑战。

AI 整理
  • 本体 SDK 与控制
  • 具身模型
  • 端侧部署

原文链接：Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents（arXiv 2608.19794 · 发布日期：2026-08-20）

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

本文综述LLM、知识库与推理能力如何融合迈向GEI，提出概念框架并梳理具身智能范式与关键挑战。

核心要点 ​

  • 动机：LLM、结构化知识库与推理能力的汇聚，被视为通向GEI的有前景路径。
  • 方法：综述LLM架构、预训练和推理机制，以及与外部知识源和结构化推理框架的交互。
  • 框架：提出LLM、KB、RA与具身协同的概念模型，用于指导感知、推理与行动。
  • 挑战：识别高效部署、闭环知识集成、神经符号混合推理、感知行动落地和持续学习。

验证范围与局限：本文为综述，所提框架是概念性指导模型，而非已实现的工程架构。

英文摘要 (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.

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

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2608.19794：Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents访问 2026-10-21