MetaGPT: Meta Programming for Multi-Agent Collaborative Framework

by   Sirui Hong, et al.

Recently, remarkable progress has been made in automated task-solving through the use of multi-agent driven by large language models (LLMs). However, existing LLM-based multi-agent works primarily focus on solving simple dialogue tasks, and complex tasks are rarely studied, mainly due to the LLM hallucination problem. This type of hallucination becomes cascading when naively chaining multiple intelligent agents, resulting in a failure to effectively address complex problems. Therefore, we introduce MetaGPT, an innovative framework that incorporates efficient human workflows as a meta programming approach into LLM-based multi-agent collaboration. Specifically, MetaGPT encodes Standardized Operating Procedures (SOPs) into prompts to enhance structured coordination. Subsequently, it mandates modular outputs, empowering agents with domain expertise comparable to human professionals, to validate outputs and minimize compounded errors. In this way, MetaGPT leverages the assembly line paradigm to assign diverse roles to various agents, thereby establishing a framework that can effectively and cohesively deconstruct complex multi-agent collaborative problems. Our experiments on collaborative software engineering benchmarks demonstrate that MetaGPT generates more coherent and correct solutions compared to existing chat-based multi-agent systems. This highlights the potential of integrating human domain knowledge into multi-agent systems, thereby creating new opportunities to tackle complex real-world challenges. The GitHub repository of this project is publicly available on:


page 3

page 7


AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents

Autonomous agents empowered by Large Language Models (LLMs) have undergo...

Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

In this paper, we present a novel framework for enhancing the capabiliti...

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Text evaluation has historically posed significant challenges, often dem...

The Multi-Agent Programming Contest: A résumé

The Multi-Agent Programming Contest, MAPC, is an annual event organized ...

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

This technical report presents AutoGen, a new framework that enables dev...

Blind Judgement: Agent-Based Supreme Court Modelling With GPT

We present a novel Transformer-based multi-agent system for simulating t...

MindAgent: Emergent Gaming Interaction

Large Language Models (LLMs) have the capacity of performing complex sch...

Please sign up or login with your details

Forgot password? Click here to reset