HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems
Yihan Xia, Taotao Wang, Shengli Zhang, Zhangyuhua Weng, Bin Cao, Soung Chang Liew
Abstract
Recent advances in LLM-based multi-agent systems have demonstrated remarkable capabilities in complex decision-making scenarios such as financial trading and software engineering. However, evaluating each individual agent’s effectiveness and online optimization of underperforming agents remain open challenges. To address these issues, we present HiveMind, a self-adaptive framework designed to optimize LLM multi-agent collaboration through contribution analysis. At its core, HiveMind introduces Contribution-Guided Online Prompt Optimization (CG-OPO), which autonomously refines agent prompts based on their quantified contributions. We first propose the Shapley value as a grounded metric to quantify each agent
BibTeX
@inproceedings{aaai2026_hivemindcontribu,
title = {HiveMind: Contribution-Guided Online Prompt Optimization of LLM Multi-Agent Systems},
author = {Yihan Xia and Taotao Wang and Shengli Zhang and Zhangyuhua Weng and Bin Cao and Soung Chang Liew},
booktitle = {AAAI 2026},
year = {2026}
}