MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
DeepWisdom · King Abdullah University of Science and Technology · Wuhan University · Xiamen University · Department of Computer Science and Engineering, The Chinese University of Hong Kong · The Chinese University of Hong Kong, Shenzhen · Hong Kong polytechnic university · nanjing university · CUHKsz · University of Pennsylvania, University of Pennsylvania · The Chinese University of Hong Kong · University of California, Berkeley · NNAISENSE, Swiss AI Lab IDSIA (USI & SUPSI)
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
Recently, remarkable progress has been made on automated problem solving through societies of agents based on large language models (LLMs). Previous LLM-based multi-agent systems can already solve simple dialogue tasks. More complex tasks, however, face challenges 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.