Skip to yearly menu bar Skip to main content


Oral

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

Sirui Hong · Mingchen Zhuge · Jonathan Chen · Xiawu Zheng · Yuheng Cheng · Jinlin Wang · Ceyao Zhang · zili wang · Steven Yau · Zijuan Lin · Liyang Zhou · Chenyu Ran · Lingfeng Xiao · Chenglin Wu · J├╝rgen Schmidhuber

Halle A 8 - 9
[ ] [ Visit Oral 2A ]
Tue 7 May 6:45 a.m. — 7 a.m. PDT

Abstract:

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.

Chat is not available.