Towards Citizen-Centric Multiagent Systems Based on Large Language Models

Zhaoxing Li, Vahid Yazdanpanah, Stefan Sarkadi, Yulan He, Elnaz Shafipour, Sebastian Stein

Abstract: The rapid evolution of Large Language Models (LLMs), exemplified by GPT-4, has ushered in a transformative era in artificial intelligence (AI). This paper introduces the concept of Citizen-Centric Multiagent Systems based on Large Language Models (C-LLMAS) and advocates for LLMs as pivotal technology for this vision. We present a framework that places citizens at the core of multiagent systems, ensuring user-friendly interactions, bidirectional feedback, and dynamic user participation. Key contributions include proposing a framework for C-LLMAS that integrates LLMs to enhance citizen engagement and feedback loops; identifying and discussing research challenges such as personalized citizen modeling, safeguarding citizen interests, and improving explainability; and highlighting research opportunities in domains like transportation, healthcare, and education. By addressing these challenges and exploring these opportunities, this paper aims to integrate LLMs into C-LLMAS responsibly, enhancing citizens’ social good and trust in AI systems.