Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xudong, Zhang, Chaoning, Li, Chenghao, Chen, Shuxu, Sun, Qigan, Zhang, Jiaquan, Puspitasari, Fachrina Dewi, Kim, Tae-Ho, Wei, Jiwei, Zhang, Malu, Wang, Guoqing, Yang, Yang, Shen, Heng Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913048594219008
author Wang, Xudong
Zhang, Chaoning
Li, Chenghao
Chen, Shuxu
Sun, Qigan
Zhang, Jiaquan
Puspitasari, Fachrina Dewi
Kim, Tae-Ho
Wei, Jiwei
Zhang, Malu
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
author_facet Wang, Xudong
Zhang, Chaoning
Li, Chenghao
Chen, Shuxu
Sun, Qigan
Zhang, Jiaquan
Puspitasari, Fachrina Dewi
Kim, Tae-Ho
Wei, Jiwei
Zhang, Malu
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
contents Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems. Despite these advances, high-quality reasoning remains heavily reliant on manual static prompts and is sensitive to decoding configurations and task distributions, leading to performance fluctuations and limited transferability. Existing automatic prompt optimization methods typically adopt single-agent local search, failing to simultaneously optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements. To address this limitation, we propose Agent-GWO, a dynamic prompt optimization framework for complex reasoning. Specifically, we unify prompt templates and decoding hyperparameters as inheritable agent configurations. By leveraging the leader-follower mechanism of the Grey Wolf Optimizer (GWO), we automatically select three leader agents ($α$, $β$, and $δ$) to guide the collaborative updates of the remaining agents, enabling iterative convergence toward robust optimal reasoning configurations that can be seamlessly integrated for inference. Extensive experiments on multiple mathematical and hybrid reasoning benchmarks across diverse LLM backbones show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods. The code will be released publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18612
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models
Wang, Xudong
Zhang, Chaoning
Li, Chenghao
Chen, Shuxu
Sun, Qigan
Zhang, Jiaquan
Puspitasari, Fachrina Dewi
Kim, Tae-Ho
Wei, Jiwei
Zhang, Malu
Wang, Guoqing
Yang, Yang
Shen, Heng Tao
Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems. Despite these advances, high-quality reasoning remains heavily reliant on manual static prompts and is sensitive to decoding configurations and task distributions, leading to performance fluctuations and limited transferability. Existing automatic prompt optimization methods typically adopt single-agent local search, failing to simultaneously optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements. To address this limitation, we propose Agent-GWO, a dynamic prompt optimization framework for complex reasoning. Specifically, we unify prompt templates and decoding hyperparameters as inheritable agent configurations. By leveraging the leader-follower mechanism of the Grey Wolf Optimizer (GWO), we automatically select three leader agents ($α$, $β$, and $δ$) to guide the collaborative updates of the remaining agents, enabling iterative convergence toward robust optimal reasoning configurations that can be seamlessly integrated for inference. Extensive experiments on multiple mathematical and hybrid reasoning benchmarks across diverse LLM backbones show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods. The code will be released publicly.
title Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models
topic Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2604.18612