Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents
This addresses challenges for storywriters in managing character dynamics, though it is incremental as it builds on existing LLM and multi-agent techniques for a specific domain.
The authors tackled the problem of storywriters struggling to create interconnected characters by developing Constella, an LLM-based multi-agent tool that suggests related characters, reveals inner thoughts, and manifests relationships, with a deployment study (N=11) showing it enabled expansive character communities and deeper relationship understanding.
Creating a cast of characters by attending to their relational dynamics is a critical aspect of most long-form storywriting. However, our formative study (N=14) reveals that writers struggle to envision new characters that could influence existing ones, to balance similarities and differences among characters, and to intricately flesh out their relationships. Based on these observations, we designed Constella, an LLM-based multi-agent tool that supports storywriters' interconnected character creation process. Constella suggests related characters (FRIENDS DISCOVERY feature), reveals the inner mindscapes of several characters simultaneously (JOURNALS feature), and manifests relationships through inter-character responses (COMMENTS feature). Our 7-8 day deployment study with storywriters (N=11) shows that Constella enabled the creation of expansive communities composed of related characters, facilitated the comparison of characters' thoughts and emotions, and deepened writers' understanding of character relationships. We conclude by discussing how multi-agent interactions can help distribute writers' attention and effort across the character cast.