Knowledge Synthesis in Dynamic Human-Swarm Interactions Using LLMs

Abstract

Collectively exploring and understanding an environment is an open challenge, particularly in dynamic settings where agents must rely on limited information that may only be intermittently available. In this paper, we focus on how agents can maximize information capture in these contexts. As agents encounter an informant with information to communicate—such as a human collaborator sharing a transient observation—they aggregate this data into a textual description of the environment using an LLM. We show that agents capture environmental information faster when sharing information with other members of the swarm. While strictly ephemeral information may never be fully captured, social learning enables agents to acquire significantly more information, demonstrating the critical importance of information sharing between agents.