Papers
arxiv:2510.12246

PromptFlow: Training Prompts Like Neural Networks

Published on Oct 14
Authors:
,
,
,

Abstract

PromptFlow is a modular framework for automated prompt engineering that uses reinforcement learning and gradient-based meta-learning to optimize prompts for large language models with minimal task-specific training data.

AI-generated summary

Large Language Models (LLMs) have demonstrated profound impact on Natural Language Processing (NLP) tasks. However, their effective deployment across diverse domains often require domain-specific adaptation strategies, as generic models may underperform when faced with specialized data distributions. Recent advances in prompt engineering (PE) offer a promising alternative to extensive retraining by refining input instructions to align LLM outputs with task objectives. This paradigm has emerged as a rapid and versatile approach for model fine-tuning. Despite its potential, manual prompt design remains labor-intensive and heavily depends on specialized expertise, often requiring iterative human effort to achieve optimal formulations. To address this limitation, automated prompt engineering methodologies have been developed to systematically generate task-specific prompts. However, current implementations predominantly employ static update rules and lack mechanisms for dynamic strategy selection, resulting in suboptimal adaptation to varying NLP task requirements. Furthermore, most methods treat and update the whole prompts at each step, without considering editing prompt sections at a finer granularity. At last, in particular, the problem of how to recycle experience in LLM is still underexplored. To this end, we propose the PromptFlow, a modular training framework inspired by TensorFlow, which integrates meta-prompts, operators, optimization, and evaluator. Our framework can be equipped with the latest optimization methods and autonomously explores optimal prompt refinement trajectories through gradient-based meta-learning, requiring minimal task-specific training data. Specifically, we devise a reinforcement learning method to recycle experience for LLM in the PE process. Finally, we conduct extensive experiments on various datasets, and demonstrate the effectiveness of PromptFlow.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.12246 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.12246 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.12246 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.