SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2

TL;DR

SysTemp is a multi-agent system designed to automate and enhance the creation of SysML v2 models from natural language descriptions, addressing challenges like complex syntax and limited training data.

Contribution

The paper introduces SysTemp, a novel multi-agent system with a template generator to facilitate SysML v2 model generation from natural language.

Findings

Improves quality of SysML v2 model generation

Addresses syntax complexity and data scarcity issues

Demonstrates potential through evaluation

Abstract

The automatic generation of SysML v2 models represents a major challenge in the engineering of complex systems, particularly due to the scarcity of learning corpora and complex syntax. We present SysTemp, a system aimed at facilitating and improving the creation of SysML v2 models from natural language specifications. It is based on a multi-agent system, including a template generator that structures the generation process. We discuss the advantages and challenges of this system through an evaluation, highlighting its potential to improve the quality of the generations in SysML v2 modeling.