AutoGRAMS: Autonomous Graphical Agent Modeling Software
This provides a tool for developers to design sophisticated AI agents, but it is incremental as it builds on existing graph-based and agent modeling approaches.
The paper tackles the problem of programming multi-step interactions with language models by introducing the AutoGRAMS framework, which represents AI agents as graphs that combine language modeling and traditional code for improved interpretability, controllability, and safety.
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 .