Saved in:
Bibliographic Details
Main Authors: Kagaya, Tomoyuki, Yuan, Thong Jing, Lou, Yuxuan, Karlekar, Jayashree, Pranata, Sugiri, Kinose, Akira, Oguri, Koki, Wick, Felix, You, Yang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.03610
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910319100559360
author Kagaya, Tomoyuki
Yuan, Thong Jing
Lou, Yuxuan
Karlekar, Jayashree
Pranata, Sugiri
Kinose, Akira
Oguri, Koki
Wick, Felix
You, Yang
author_facet Kagaya, Tomoyuki
Yuan, Thong Jing
Lou, Yuxuan
Karlekar, Jayashree
Pranata, Sugiri
Kinose, Akira
Oguri, Koki
Wick, Felix
You, Yang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_03610
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
Kagaya, Tomoyuki
Yuan, Thong Jing
Lou, Yuxuan
Karlekar, Jayashree
Pranata, Sugiri
Kinose, Akira
Oguri, Koki
Wick, Felix
You, Yang
Machine Learning
Artificial Intelligence
Computation and Language
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.
title RAP: Retrieval-Augmented Planning with Contextual Memory for Multimodal LLM Agents
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2402.03610