一句话：提出 CogniSim 生态系统，将 LLM 与多智能体系统结合并引入心理理论，用于敏捷软件工程并仿真团队配置效果。
本文提出面向敏捷软件工程的多智能体生态系统 CogniSim，旨在把多智能体系统（MAS）与大语言模型（LLM）结合起来改进软件开发流程。系统采用动态上下文技术为智能体建立画像，并引入心理理论（Theory of Mind）增强智能体之间的协作；智能体分别扮演开发者、执行者、质量检查者与方法学评审者等角色，协作完成问题分析、方案提出、计划构建与验证，产出文档、模型与 UML 图等工件，并遵循预设的质量与性能指标。该生态系统还可仿真不同团队配置对问题解决效果的影响，帮助组织识别最优团队结构。案例研究与仿真实验展示了其实际应用价值。
A cognitive multi-agent ecosystem designed for efficient software engineering using Agile methodologies can significantly improve software development processes. Key components include the integration of Multi-Agent Systems (MAS) and Large Language Models (LLMs), utilizing Dynamic Context techniques for agent profiling, and Theory of Mind to enhance collaboration. The CogniSim Ecosystem analyzes problems, proposes solutions, constructs and validates plans, and coordinates specialized agents playing roles such as developers, executors, quality checkers, and methodology reviewers. These agents produce documentation, models, and diagrams (e.g., UML) while adhering to predefined quality and performance measures. The ecosystem also simulates the impact of various team configurations on problem-solving effectiveness, helping organizations identify optimal team structures. Case studies and simulations demonstrate its practical applications.