A New Paradigm for Effective LLM-Agent Discovery and Dynamic Creation of Trusted Multiagent Systems Based on Social Relationships

Recent advances in large language model-based multiagent systems (LLM-MASs) are revealing significant potential for streamlining workflows in many areas, including the Internet of Things (IoT), where their integration offers new opportunities to improve decision-making and system interaction. Nevertheless, the proliferation of large language model (LLM)-based agents worldwide creates significant challenges in identifying and selecting suitable and trusted agents to create multiagent systems (MASs) to tackle complex tasks at scale. To help address this issue, this article presents an innovative paradigm that enables fully decentralized agent and workflow discovery through social relationships among LLM-based agents, as well as the dynamic creation of trusted social LLM-MAS. A possible reference architecture with its main components is presented, and the basic relationship types that can be established among a global population of LLM agents are illustrated, as well as mechanisms that allow agents to discover peers leveraging navigable social graphs rather than centralized searches. We also discuss possible ways to achieve a trust and reputation system that leverages these social relationships to filter peer-reviewed agents. The resulting social LLM-MAS paradigm envisioned will represent a mature generational leap over the two-tier operational/knowledge-based frameworks increasingly available worldwide but still disconnected and nonsynergistic.