Towards Improving Large Language Models’ Planning Capabilities onWoT Thing Descriptions by Generating Python Objects as Intermediary Representations

This paper presents a novel method for plan generation with Large Language Model(LLM). We propose utilizing
Web-of-Thing Thing Descriptions (WoT TD) to inform the LLM about available devices for interaction. We
investigate a novel pipeline in which: (1) The WoT TD gets translated into a Python class, (2) The task in natural
language gets translated into code that interact with this class, (3) The generated code gets executed to obtain the
plan. We evaluate our approach featuring 6 different state of the art LLMs. We get performance improvements
of up to 12%, when comparing our approach against existing LLM-based planning methods. Furthermore, we
explore the influence of different aspects of WoT TDs on planning capabilities. This research paves the way
towards more potent LLM planning models by introducing Python classes as intermediaries, simplifying the final
planning task while leveraging standardized and accessible domain knowledge provided by WoT TDs.