ChatBDI: Think BDI, Talk LLM

This paper describes ChatBDI, a framework for extending Beliefs-Desires-Intentions (BDI) agents with the ability to communicate with humans exploiting Large Language Models (LLMs). The ChatBDI integration of BDI agents and LLMs relies on the Knowledge Query and Manipulation Language (KQML) as the intermediary language between humans and agents, and Jason - inside the JaCaMo framework - as the implementation language. The purpose of ChatBDI is not only to create brand new 'BDI speakers', but also to add communication capabilities to existing BDI agents without altering their source code. This 'chattification' serves a double purpose: by exploiting the BDI model, it provides an 'intentional brain' to LLMs, hence addressing one of their major limitations as speakers - the lack of intentionality; by exploiting the generative power of LLMs, it adds a creative and fluent 'language actuator' to BDI agents.