如何开发复杂、庞大的Ｍｕｌｔｉ－ａｇｅｎｔ系统是目前人们关心的一个重要研究课题．文中提出了Ｍｕｌｔｉ－ａｇｅｎｔ系统中Ａｇｅｎｔ计算的理论框架，以提供方法和概念体系用于刻画和描述Ｍｕｌｔｉ－ａｇｅｎｔ系统的需求、指导系统设计．文中提出了Ａｇｅｎｔ的一种新的体系结构——ＢＩＣＣ体系结构，即Ａｇｅｎｔ是由信念（ｂｅｌｉｅｆ）、意愿（ｉｎｔｅｎｔｉｏｎ）、能力（ｃａｐａｂｉｌｉｔｙ）、承诺（ｃｏｍ ｍ ｉｔｍ ｅｎｔ）构成的意向系统．基于Ｍｕｌｔｉ－ａｇｅｎｔ系统计算的逻辑框架，文中给出了构成Ａｇｅｎｔ体系结构各个认知成份的语义定义，分析了Ａｇｅｎｔ是如何基于该体系结构来进行计算的，最后研究和验证了在动态、不确定的Ｍｕｌｔｉ－ａｇｅｎｔ系统中Ａｇｅｎｔ计算的活性和安全性问题 How to develop a complex and huge Multi-agent system is an important research subject that people are concerned about now. In this paper, the theoretical framework of Agent computing in Multi-agent system is proposed to provide the method and concept system for describing and describing the requirements of Multi-agent system and guiding the design of the system. In this paper, a new architecture of Agent - BICC architecture is proposed. Agent is an intention system composed of belief, intention, capability and commitment. Based on the logical framework of multi-agent system computing, the semantic definitions of various cognitive components that make up Agent architecture are given in this paper, and how Agent is calculated based on this architecture is analyzed. Finally, the dynamic and uncertain Agent Multi-Agent system in the calculation of the activity and security issues