MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913569188085760 |
|---|---|
| author | Hong, Sirui Zhuge, Mingchen Chen, Jiaqi Zheng, Xiawu Cheng, Yuheng Zhang, Ceyao Wang, Jinlin Wang, Zili Yau, Steven Ka Shing Lin, Zijuan Zhou, Liyang Ran, Chenyu Xiao, Lingfeng Wu, Chenglin Schmidhuber, Jürgen |
| author_facet | Hong, Sirui Zhuge, Mingchen Chen, Jiaqi Zheng, Xiawu Cheng, Yuheng Zhang, Ceyao Wang, Jinlin Wang, Zili Yau, Steven Ka Shing Lin, Zijuan Zhou, Liyang Ran, Chenyu Xiao, Lingfeng Wu, Chenglin Schmidhuber, Jürgen |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_00352 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework Hong, Sirui Zhuge, Mingchen Chen, Jiaqi Zheng, Xiawu Cheng, Yuheng Zhang, Ceyao Wang, Jinlin Wang, Zili Yau, Steven Ka Shing Lin, Zijuan Zhou, Liyang Ran, Chenyu Xiao, Lingfeng Wu, Chenglin Schmidhuber, Jürgen Artificial Intelligence Multiagent 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 |
| title | MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2308.00352 |