arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.10049cs.CLcs.AI
收藏

AutoGRAMS:自主图形化智能体建模软件

AutoGRAMS: Autonomous Graphical Agent Modeling Software

Autograms AI(奥图格拉姆斯人工智能公司)

Ben Krause, Lucia Chen, Emmanuel Kahembwe

AI总结:

本研究提出AutoGRAMS框架,以图结构表示AI智能体,支持节点执行语言指令或代码、转移由语言决策或分支逻辑控制,可设计复杂自指智能体,提升可解释性等,已开源。

摘要:

我们介绍用于对语言模型的多步交互进行编程的AutoGRAMS(自主图形化智能体建模软件)框架。AutoGRAMS将AI智能体表示为图,其中每个节点既可执行语言建模指令,也可执行传统代码。同样地,图中的转移既可由语言建模决策控制,也可由传统分支逻辑控制。AutoGRAMS支持使用变量作为内存,并允许节点调用其他AutoGRAMS图作为函数。我们展示了如何使用AutoGRAMS设计高度复杂的智能体,包括能够修改自身图的自指智能体。AutoGRAMS的以图为中心的方法有助于提升AI智能体设计、开发和部署过程中的可解释性、可控性与安全性。我们在https://github.com/autograms/autograms 开源了该框架。

英文摘要:

We introduce the AutoGRAMS framework for programming multi-step interactions with language models. AutoGRAMS represents AI agents as a graph, where each node can execute either a language modeling instruction or traditional code. Likewise, transitions in the graph can be governed by either language modeling decisions or traditional branch logic. AutoGRAMS supports using variables as memory and allows nodes to call other AutoGRAMS graphs as functions. We show how AutoGRAMS can be used to design highly sophisticated agents, including self-referential agents that can modify their own graph. AutoGRAMS's graph-centric approach aids interpretability, controllability, and safety during the design, development, and deployment of AI agents. We provide our framework as open source at https://github.com/autograms/autograms .

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。

↑