Saved in:
Bibliographic Details
Main Authors: Krause, Ben, Chen, Lucia, Kahembwe, Emmanuel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.10049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910526988091392
author Krause, Ben
Chen, Lucia
Kahembwe, Emmanuel
author_facet Krause, Ben
Chen, Lucia
Kahembwe, Emmanuel
contents 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 .
format Preprint
id arxiv_https___arxiv_org_abs_2407_10049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AutoGRAMS: Autonomous Graphical Agent Modeling Software
Krause, Ben
Chen, Lucia
Kahembwe, Emmanuel
Computation and Language
Artificial Intelligence
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 .
title AutoGRAMS: Autonomous Graphical Agent Modeling Software
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2407.10049