Constella: Supporting Storywriters' Interconnected Character Creation through LLM-based Multi-Agents

2025-07-08

AI Summary

Narrative creators face significant challenges in constructing cohesive character ensembles for long-form storytelling, including difficulty in designing novel characters, imbalanced similarity-dissimilarity trade-offs among characters, and superficial relationship modeling. To address these issues, we propose a large language model (LLM)-based multi-agent collaborative framework that enables deep, interdependent character generation through three core techniques: automated character relation discovery, visualizable inner-world modeling, and cross-character dynamic interaction response. The system integrates relation recommendation, joint log generation, and interactive commentary simulation modules to facilitate effective attention allocation at the ensemble level. Empirical evaluation demonstrates substantial improvements in ensemble scale and emotional contrast, alongside enhanced granularity and consistency in interpersonal relationship modeling. Our approach establishes a scalable, interpretable paradigm for character co-generation in narrative AI.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Helps writers envision new characters influencing existing ones
• Balances similarities and differences among story characters
• Supports intricate development of character relationships

Innovation

• LLM-based multi-agent tool for character creation
• Simultaneous inner mindscapes with JOURNALS feature
• Inter-character responses via COMMENTS feature