Click here to download project base paper
Abstract:
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
Meta GPT, an innovative meta-programming framework incorporating efficient
human workflows into LLM-based multi-agent collaborations. Meta GPT 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. Meta GPT 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, Meta GPT generates more coherent solutions than previous chat-based multi-agent systems. Our project can be found at https://github.com/geekan/MetaGPT
