OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following

Haochen Shi, Zhiyuan Sun, Xingdi Yuan, Marc-Alexandre Côté, Bang Liu


Abstract
Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions. Recent advancements have seen a surge in employing large language models (LLMs) within a framework-centric approach to enhance performance in embodied learning tasks, including EIF. Despite these efforts, there exists a lack of a unified understanding regarding the impact of various components—ranging from visual perception to action execution—on task performance. To address this gap, we introduce OPEx, a comprehensive framework that delineates the core components essential for solving embodied learning tasks: Observer, Planner, and Executor. Through extensive evaluations, we provide a deep analysis of how each component influences EIF task performance. Furthermore, we innovate within this space by integrating a multi-agent design into the Planner component of our LLM-centric architecture, further enhancing task performance. Our findings reveal that LLM-centric design markedly improves EIF outcomes, identify visual perception and low-level action execution as critical bottlenecks, and demonstrate that augmenting LLMs with a multi-agent framework further elevates performance.
Anthology ID:
2024.acl-long.37
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
622–636
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.37/
DOI:
10.18653/v1/2024.acl-long.37
Bibkey:
Cite (ACL):
Haochen Shi, Zhiyuan Sun, Xingdi Yuan, Marc-Alexandre Côté, and Bang Liu. 2024. OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 622–636, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following (Shi et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.acl-long.37.pdf