Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models
arXiv:2605.29625v1 Announce Type: new Abstract: The topic of Co-creation, i.e., AI agents interacting with humans to generate outputs (e.g., art), has gained significant attention recently. However, most studies focus on adult-human interactions in a digital setting. This paper explores a novel ludic co-creation scenario involving children and Large Language Models (LLMs) interacting through a physical board game to create written stories. Our goal is to develop a multi-agent framework capable of producing high-quality narratives suitable for young players. At the core of our approach is an it
The rapid advancements in large language models enable more sophisticated and contextual interactions, making co-creation with AI agents feasible beyond simple digital interfaces.
This development highlights the expanding application of AI agents into complex, human-centric, and even child-focused creative processes, hinting at broader societal integration.
The scope of AI agent interaction shifts from purely digital and adult-oriented tasks to tangible, multi-modal, and age-diverse collaborative activities, expanding the developmental pathways for AI.
- · AI Agent Developers
- · Ed-tech companies
- · Game designers
- · Children/Education sector
- · Traditional content creation models
- · Monolithic AI architectures
AI agents move beyond simple task automation to become interactive co-creators in educational and entertainment settings.
This deepens the human-AI interface, potentially fostering new forms of creativity and learning, especially in younger demographics.
The success of physical, multi-agent co-creation frameworks could accelerate broader adoption of AI in diverse human-machine interaction contexts, including professional creative fields.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI