Bring game characters to the social space: Developing storytelling community AI agents driven by LLMs

AI agents driven by Large Language Models (LLMs) are now ubiquitous in our daily life, so can they bring characters from games into reality? We address the integration of storytelling and AI agents driven by LLMs to develop engaging and believable fictional characters in community settings. Motivated by the potential of fictional characters to enhance social interactions, we introduce Storytelling Community AI Agents (SCAs) and the concept of story engineering to transform fictional game characters into ”live” social entities within player communities. Our story engineering process includes three steps: (1) Character and story creation, defining the SCA’s personality and worldview, (2) Presenting Live Stories to the Community, allowing the agent to recount challenges and seek suggestions, and (3) Communication with community members, enabling interaction between the agent and users. We employed the LLM GPT-3 to drive our SCAs, “David” and “Catherine,” and evaluated their performance in an online gaming community, “DE (Alias),” on Discord. Our mixed-method analysis, based on questionnaires (N=15) and interviews (N=8) with community members, reveals that storytelling significantly enhances the engagement and believability of AI agents in community settings.