DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human Reflection

2026-02-05

AI Summary

This work addresses the limitations of existing AI script polishing tools, which often fail to simultaneously capture characters’ internal experiences and the narrative’s holistic perspective, thereby inadequately supporting screenwriters’ deep reflection. To overcome this, we propose DuoDrama, a novel system that introduces a dual-role switching mechanism grounded in performance theory and screenwriting practice. Our ExReflect workflow first generates contextualized content from an “Experiencer” role, then switches to an “Evaluator” role to produce structured feedback, effectively decoupling experiential immersion from critical assessment to better align with screenwriters’ cognitive processes. In a study with 14 professional screenwriters, DuoDrama significantly improved feedback quality, script alignment, and the effectiveness, depth, and diversity of reflective engagement.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

AI has been increasingly integrated into screenwriting practice. In refinement, screenwriters expect AI to provide feedback that supports reflection across the internal perspective of characters and the external perspective of the overall story. However, existing AI tools cannot sufficiently coordinate the two perspectives to meet screenwriters'needs. To address this gap, we present DuoDrama, an AI system that generates feedback to assist screenwriters'reflection in refinement. To enable DuoDrama, based on performance theories and a formative study with nine professional screenwriters, we design the Experience-Grounded Feedback Generation Workflow for Human Reflection (ExReflect). In ExReflect, an AI agent adopts an experience role to generate experience and then shifts to an evaluation role to generate feedback based on the experience. A study with fourteen professional screenwriters shows that DuoDrama improves feedback quality and alignment and enhances the effectiveness, depth, and richness of reflection. We conclude by discussing broader implications and future directions.

Problem

• screenplay refinement
• human reflection
• AI feedback
• character perspective
• story perspective

Innovation

• LLM-assisted reflection
• Experience-Grounded Feedback
• Screenplay refinement
• Dual-perspective feedback
• Human-AI collaboration