PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

TL;DR

PromptAgent automates expert-level prompt creation for large language models by framing prompt optimization as a strategic planning problem and using Monte Carlo tree search, leading to high-quality, domain-insightful prompts.

Contribution

This paper introduces PromptAgent, a novel framework that applies strategic planning and Monte Carlo tree search to automate expert-level prompt optimization for LLMs.

Findings

PromptAgent outperforms existing prompt optimization methods on 12 diverse tasks.

It efficiently generates detailed, domain-specific prompts comparable to human-crafted ones.

The approach demonstrates strong generalizability across different NLP domains.

Abstract

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task. However, automating the generation of such expert-level prompts remains elusive. Existing prompt optimization methods tend to overlook the depth of domain knowledge and struggle to efficiently explore the vast space of expert-level prompts. Addressing this, we present PromptAgent, an optimization method that autonomously crafts prompts equivalent in quality to those handcrafted by experts. At its core, PromptAgent views prompt optimization as a strategic planning problem and employs a principled planning algorithm, rooted in Monte Carlo tree search, to strategically navigate the expert-level prompt space. Inspired by human-like trial-and-error exploration, PromptAgent induces precise expert-level insights and in-depth instructions by reflecting on model errors and generating constructive error feedback. Such a novel framework allows the agent to iteratively examine intermediate prompts (states), refine them based on error feedbacks (actions), simulate future rewards, and search for high-reward paths leading to expert prompts. We apply PromptAgent to 12 tasks spanning three practical domains: BIG-Bench Hard (BBH), as well as domain-specific and general NLP tasks, showing it significantly outperforms strong Chain-of-Thought and recent prompt optimization baselines. Extensive analyses emphasize its capability to craft expert-level, detailed, and domain-insightful prompts with great efficiency and generalizability.