Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft

Kranti Ch, Sherzod Hakimov, David Schlangen


Abstract
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.
Anthology ID:
2024.findings-emnlp.652
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11159–11170
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.652/
DOI:
10.18653/v1/2024.findings-emnlp.652
Bibkey:
Cite (ACL):
Kranti Ch, Sherzod Hakimov, and David Schlangen. 2024. Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11159–11170, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Retrieval-Augmented Code Generation for Situated Action Generation: A Case Study on Minecraft (Ch et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.652.pdf