The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM capabilities, enabling deeper integration into MAS through enhanced knowledge retrieval and reasoning. However, these advancements introduce critical challenges: LLM agents exhibit inherent unpredictability, and uncertainties in their outputs can compound across interactions, threatening system stability. To address these risks, a human-centered design approach with active dynamic moderation is essential. Such an approach enhances traditional passive oversight by facilitating coherent inter-agent communication and effective system governance, allowing MAS to achieve desired outcomes more efficiently.
@article{arxiv.2502.01714,
title = {Position: Towards a Responsible LLM-empowered Multi-Agent Systems},
author = {Jinwei Hu and Yi Dong and Shuang Ao and Zhuoyun Li and Boxuan Wang and Lokesh Singh and Guangliang Cheng and Sarvapali D. Ramchurn and Xiaowei Huang},
journal= {arXiv preprint arXiv:2502.01714},
year = {2025}
}