DelvePO: Direction-Guided Self-Evolving Framework for Flexible Prompt Optimization

ICLR 2026 Conference Submission15620 Authors

Keywords: Prompt Optimization, Prompt Engineering, Evolutionary Algorithm, Large Language Models

TL;DR: This paper presents a task-agnostic, component-customizable and flexible framework to optimize the prompts in a self-evolve manner. To the best of our knowledge, this is the first work that introduces memory mechanism to PO.

Abstract:

Prompt Optimization has emerged as a crucial approach due to
its capabilities in steering Large Language Models to solve
various tasks. However, current works mainly rely on the random
rewriting ability of LLMs, and the optimization process generally
focus on specific influencing factors, which makes it easy to fall into local optimum.
Besides, the performance of the optimized prompt is often unstable,
which limits its transferability in different tasks.
To address the above challenges, we propose $\textbf{DelvePO}$
($\textbf{D}$irection-Guid$\textbf{e}$d Se$\textbf{l}$f-E$\textbf{v}$olving
Framework for Fl$\textbf{e}$xible $\textbf{P}$rompt $\textbf{O}$ptimization),
a task-agnostic framework to optimize prompts
in self-evolve manner. In our framework, we decouple
prompts into different components that can be used to explore
the impact that different factors may have on various tasks.
On this basis, we introduce working memory, through which
LLMs can alleviate the deficiencies caused by their own uncertainties
and further obtain key insights to guide the generation of
new prompts. Extensive experiments conducted on different
tasks covering various domains for both open- and
closed-source LLMs, including DeepSeek-R1-Distill-Llama-8B, Qwen2.5-7B-Instruct and GPT-4o-mini. Experimental results show that
DelvePO consistently outperforms previous SOTA methods
under identical experimental settings, demonstrating
its effectiveness and transferability across different tasks.

Primary Area: foundation or frontier models, including LLMs

Submission Number: 15620