MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
This addresses the challenge of improving multi-agent collaboration for complex problem-solving in AI, though it appears incremental as it builds on existing LLM-based systems with workflow enhancements.
The paper tackles the problem of logic inconsistencies and cascading hallucinations in LLM-based multi-agent systems for complex tasks by introducing MetaGPT, a meta-programming framework that incorporates human workflows and Standardized Operating Procedures (SOPs) into prompt sequences, resulting in more coherent solutions on collaborative software engineering benchmarks compared to previous chat-based systems.
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