Remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Existing LLM-based multi-agent systems can already solve simple dialogue tasks. Solutions to more complex tasks, however, are complicated through logic inconsistencies due to cascading hallucinations caused by naively chaining LLMs. Here we introduce MetaGPT, an innovative meta-programming framework incorporating efficient human workflows into LLM-based multi-agent collaborations. MetaGPT encodes Standardized Operating Procedures (SOPs) into prompt sequences for more streamlined workflows, thus allowing agents with human-like domain expertise to verify intermediate results and reduce errors. MetaGPT utilizes an assembly line paradigm to assign diverse roles to various agents, efficiently breaking down complex tasks into subtasks involving many agents working together. On collaborative software engineering benchmarks, MetaGPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT

翻译：基于大型语言模型（LLM）的智能体社会已在自动问题求解领域取得显著进展。现有基于LLM的多智能体系统已能解决简单对话任务。然而，由于简单链式调用LLM导致的级联幻觉引发逻辑不一致性，使得更复杂任务的求解变得复杂。本文提出MetaGPT——一种创新的元编程框架，将高效人工工作流融入基于LLM的多智能体协作中。MetaGPT通过将标准化操作流程（SOP）编码为提示序列实现更精简的工作流，使具备类人领域专业知识的智能体能够验证中间结果并减少错误。该框架采用流水线范式为不同智能体分配差异化角色，高效地将复杂任务分解为多智能体协同处理的子任务。在协作软件工程基准测试中，MetaGPT生成的解决方案比先前基于聊天的多智能体系统更具连贯性。项目代码详见https://github.com/geekan/MetaGPT。