In the Minecraft Collaborative Building Task, two players collaborate: an Architect (A) provides instructions to a Builder (B) to assemble a specified structure using 3D blocks. In this work, we investigate the use of large language models (LLMs) to predict the sequence of actions taken by the Builder. Leveraging LLMs' in-context learning abilities, we use few-shot prompting techniques, that significantly improve performance over baseline methods. Additionally, we present a detailed analysis of the gaps in performance for future work
@article{arxiv.2406.17553,
title = {Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft},
author = {Chalamalasetti Kranti and Sherzod Hakimov and David Schlangen},
journal= {arXiv preprint arXiv:2406.17553},
year = {2024}
}