LLM-Assisted Modeling of Semantic Web-Enabled Multi-Agents Systems with AJAN
This addresses a practical problem for agent modelers using semantic web standards, offering an incremental improvement by integrating LLMs into an existing framework.
The paper tackles the difficulty of defining RDF/RDFS and SPARQL-based agent behaviors in AJAN multi-agent systems, which is error-prone and requires a high learning curve, by presenting an integrated development environment that leverages Large Language Models to assist in agent engineering.
There are many established semantic Web standards for implementing multi-agent driven applications. The AJAN framework allows to engineer multi-agent systems based on these standards. In particular, agent knowledge is represented in RDF/RDFS and OWL, while agent behavior models are defined with Behavior Trees and SPARQL to access and manipulate this knowledge. However, the appropriate definition of RDF/RDFS and SPARQL-based agent behaviors still remains a major hurdle not only for agent modelers in practice. For example, dealing with URIs is very error-prone regarding typos and dealing with complex SPARQL queries in large-scale environments requires a high learning curve. In this paper, we present an integrated development environment to overcome such hurdles of modeling AJAN agents and at the same time to extend the user community for AJAN by the possibility to leverage Large Language Models for agent engineering.