arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.00352cs.AIcs.MA
收藏

MetaGPT:面向多智能体协作框架的元编程

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

DeepWisdom(深度智慧);AI Initiative, King Abdullah University of Science and Technology(阿卜杜拉国王科技大学人工智能计划);Xiamen University(厦门大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Nanjing University(南京大学);University of Pennsylvania(宾夕法尼亚大学);University of California, Berkeley(加州大学伯克利分校);The Swiss AI Lab IDSIA/USI/SUPSI(瑞士IDSIA/USI/SUPSI人工智能实验室)
Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran… 展开作者

Sirui Hong, Mingchen Zhuge, Jiaqi Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, Jürgen Schmidhuber

AI总结:

针对现有基于大语言模型的多智能体系统处理复杂任务时因级联幻觉出现逻辑不一致的问题,提出融入人类工作流的元编程框架MetaGPT,通过编码SOP、流水线分工等提升协作效果,在软件工程基准上表现更优。

摘要:

基于大语言模型(LLMs)的智能体群体在自动化问题求解方面已取得显著进展,现有基于LLM的多智能体系统已能解决简单对话任务。然而,对于更复杂的任务,由于LLM的简单链式调用会引发级联幻觉,导致逻辑不一致,求解过程变得复杂。本文提出MetaGPT,这是一种将高效人类工作流融入基于LLM的多智能体协作的创新元编程框架。MetaGPT将标准化操作流程(SOPs)编码到提示序列中,使工作流更顺畅,从而让具备类人领域专业知识的智能体能验证中间结果、减少错误。MetaGPT采用流水线模式,为不同智能体分配多样角色,高效将复杂任务拆解为涉及多智能体协同的子任务。在协作软件工程基准测试中,MetaGPT比以往基于聊天的多智能体系统生成的解决方案更具一致性。项目地址:https://github.com/geekan/MetaGPT

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑