RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Weizhe, Koenig, Sven, Dilkina, Bistra
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910826667966464
author Chen, Weizhe
Koenig, Sven
Dilkina, Bistra
author_facet Chen, Weizhe
Koenig, Sven
Dilkina, Bistra
contents In the past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and their capacity is further expanded into the so-called LLM agents when connected with external tools. In all domains, the prompt to the LLMs has been shown to make a big difference in what the LLM would generate and thus affect the performance of the LLM agents. Therefore, automatic prompt engineering (APE) has become an important question for many researchers and users of LLMs. However, previous works in APE rely on a final checker to evaluate the performance of the given prompt -- a requirement that is hard to meet in the case of LLM agents, where intermediate feedback is easier to obtain, and the final evaluation could be expensive, inaccurate, or even missing. In this paper, we propose a novel method, \textsc{RePrompt}, which does a ``gradient descent"-like approach to optimize the step-by-step instructions in the prompts given to LLM agents, based on the chat history obtained from interactions and reflections with LLM agents. By leveraging intermediate feedback, \textsc{RePrompt} can optimize the prompt without the need for a final solution checker. We evaluate our approach on PDDL generation, TravelPlanner, and Meeting Planning to show that our method could generally improve performance for different reasoning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_11132
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents
Chen, Weizhe
Koenig, Sven
Dilkina, Bistra
Computation and Language
Artificial Intelligence
Machine Learning
In the past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and their capacity is further expanded into the so-called LLM agents when connected with external tools. In all domains, the prompt to the LLMs has been shown to make a big difference in what the LLM would generate and thus affect the performance of the LLM agents. Therefore, automatic prompt engineering (APE) has become an important question for many researchers and users of LLMs. However, previous works in APE rely on a final checker to evaluate the performance of the given prompt -- a requirement that is hard to meet in the case of LLM agents, where intermediate feedback is easier to obtain, and the final evaluation could be expensive, inaccurate, or even missing. In this paper, we propose a novel method, \textsc{RePrompt}, which does a ``gradient descent"-like approach to optimize the step-by-step instructions in the prompts given to LLM agents, based on the chat history obtained from interactions and reflections with LLM agents. By leveraging intermediate feedback, \textsc{RePrompt} can optimize the prompt without the need for a final solution checker. We evaluate our approach on PDDL generation, TravelPlanner, and Meeting Planning to show that our method could generally improve performance for different reasoning tasks.
title RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.11132