RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents

Tomoyuki Kagaya, Thong Jing Yuan, Yuxuan Lou, Jayashree Karlekar, Sugiri Pranata, Akira Kinose, Koki Oguri, Felix Wick, Yang You

Keywords: LLM, AI Agent, Memory Retrieval, Multimodal

TL;DR: We propose the Retrieval-Augmented Planning (RAP) framework. It utilizes past experiences in decision-making, offers adaptability in text-only and multimodal environments, and achieves state-of-the-art performance in agent and robotics tasks.

Abstract: Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in current decision-making processes, an innate human behavior, continues to pose significant challenges. Addressing this, we propose Retrieval-Augmented Planning (RAP) framework, designed to dynamically leverage past experiences corresponding to the current situation and context, thereby enhancing agents' planning capabilities. RAP distinguishes itself by being versatile: it excels in both text-only and multimodal environments, making it suitable for a wide range of tasks. Empirical evaluations demonstrate RAP's effectiveness, where it achieves SOTA performance in textual scenarios and notably enhances multimodal LLM agents’ performance for embodied tasks. These results highlight RAP's potential in advancing the functionality and applicability of LLM agents in complex, real-world applications.

Submission Number: 17