SAUCE: Synchronous and Asynchronous User-Customizable Environment for Multi-Agent LLM Interaction

TL;DR

SAUCE is a flexible Python platform enabling multi-agent LLM discussions with customizable synchronous and asynchronous interactions, facilitating complex social simulation with minimal coding.

Contribution

It introduces a novel asynchronous communication feature for LLMs and provides an easy-to-use, customizable environment for multi-agent discussion modeling.

Findings

Demonstrated SAUCE's effectiveness in initial experiments.

Showcased asynchronous communication modeling in LLM interactions.

Invited community adoption for diverse social simulations.

Abstract

Many human interactions, such as political debates, are carried out in group settings, where there are arbitrarily many participants, each with different views and agendas. To explore such complex social settings, we present SAUCE: a customizable Python platform, allowing researchers to plug-and-play various LLMs participating in discussions on any topic chosen by the user. Our platform takes care of instantiating the models, scheduling their responses, managing the discussion history, and producing a comprehensive output log, all customizable through configuration files, requiring little to no coding skills. A novel feature of SAUCE is our asynchronous communication feature, where models decide when to speak in addition to what to say, thus modeling an important facet of human communication. We show SAUCE's attractiveness in two initial experiments, and invite the community to use it in simulating various group simulations.