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

TL;DR

This paper introduces OPEx, a framework for analyzing LLM-centric agents in embodied instruction following, highlighting key components and demonstrating that multi-agent strategies significantly improve task performance.

Contribution

It provides a unified analysis of core components affecting EIF performance and proposes a multi-agent dialogue approach to enhance outcomes.

Findings

LLM-centric design improves EIF performance

Visual perception and action execution are bottlenecks

Multi-agent strategies further boost task success

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 deploying a multi-agent dialogue strategy on a TextWorld counterpart, 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.