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 2402.16823cs.AIcs.CLcs.LGcs.MA
收藏

作为可优化图的语言智能体

Language Agents as Optimizable Graphs

King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学);The Swiss AI Lab IDSIA, USI, SUPSI(瑞士IDSIA人工智能实验室(瑞士意大利语区大学、瑞士南部应用科学大学))

Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jürgen Schmidhuber

AI总结:

本文将基于LLM的智能体统一表示为计算图,并提出自动图优化器,通过节点级提示优化和改变图连通性的边优化来改进智能体编排,从而高效开发、集成和自动提升各种LLM智能体。

摘要:

人们提出了各种人工设计的提示工程(prompt engineering)技术来改进基于大语言模型(LLMs)的问题求解器,产生了许多不同的代码库。我们通过将基于LLM的智能体描述为计算图来统一这些方法。节点实现处理多模态数据或查询LLM的函数,边描述操作间的信息流。图可以递归组合成更大的复合图,表示智能体间协作的层级结构(其中边连接不同智能体的操作)。我们新颖的自动图优化器(1)优化节点级LLM提示(节点优化),以及(2)通过改变图连通性来改进智能体编排(边优化)。实验表明,我们的框架可用于高效开发、集成和自动改进各种LLM智能体。代码可在 https://github.com/metauto-ai/gptswarm 找到。

英文摘要:

Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. The code can be found at https://github.com/metauto-ai/gptswarm.

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。

↑