Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Murthy, Rithesh, Zhu, Ming, Yang, Liangwei, Qiu, Jielin, Tan, Juntao, Heinecke, Shelby, Xiong, Caiming, Savarese, Silvio, Wang, Huan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912500052656128
author Murthy, Rithesh
Zhu, Ming
Yang, Liangwei
Qiu, Jielin
Tan, Juntao
Heinecke, Shelby
Xiong, Caiming
Savarese, Silvio
Wang, Huan
author_facet Murthy, Rithesh
Zhu, Ming
Yang, Liangwei
Qiu, Jielin
Tan, Juntao
Heinecke, Shelby
Xiong, Caiming
Savarese, Silvio
Wang, Huan
contents Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms natural language task descriptions into high-quality prompts without requiring manual tuning or domain expertise. Promptomatix supports both a lightweight meta-prompt-based optimizer and a DSPy-powered compiler, with modular design enabling future extension to more advanced frameworks. The system analyzes user intent, generates synthetic training data, selects prompting strategies, and refines prompts using cost-aware objectives. Evaluated across 5 task categories, Promptomatix achieves competitive or superior performance compared to existing libraries, while reducing prompt length and computational overhead making prompt optimization scalable and efficient.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14241
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Murthy, Rithesh
Zhu, Ming
Yang, Liangwei
Qiu, Jielin
Tan, Juntao
Heinecke, Shelby
Xiong, Caiming
Savarese, Silvio
Wang, Huan
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms natural language task descriptions into high-quality prompts without requiring manual tuning or domain expertise. Promptomatix supports both a lightweight meta-prompt-based optimizer and a DSPy-powered compiler, with modular design enabling future extension to more advanced frameworks. The system analyzes user intent, generates synthetic training data, selects prompting strategies, and refines prompts using cost-aware objectives. Evaluated across 5 task categories, Promptomatix achieves competitive or superior performance compared to existing libraries, while reducing prompt length and computational overhead making prompt optimization scalable and efficient.
title Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2507.14241