RePrompt: Prompt Engineering for Large Language Models Agents through Reflection
Keywords: Large language models, reasoning, prompt engineering, large language model agents
TL;DR: In this paper, we propose a novel method, REPROMPT, which do prompt engineering through self-reflection instead of continuous iterations with ground-truth checkers.
Abstract: In this past year, large language models (LLMs) have had remarkable success in domains outside the traditional natural language processing, and people are starting to explore the usage of LLMs in more general and close to application domains like code generation, travel planning, and robot controls. Connecting these LLMs with great capacity and external tools, people are building the so-called LLM agents, which are supposed to help people do all kinds of work in everyday life. In all these 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 all rely on a final checker to evaluate the performance of the given prompt, which is hard to meet in the case of LLM agents where intermediate feedback is easier to get, 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 have used experiments in PDDL generation and travel planning to show that our method could generally improve the performance for different reasoning tasks.
Primary Area: foundation or frontier models, including LLMs
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 4773
Loading