Steering Emotional Dynamics for Art Therapy: Controllable Narrative Script Generation through Hierarchically Guided LLM Agents

2026-06-15

AI Summary

This work addresses the challenge that existing automatic narrative generation methods struggle to precisely control emotional trajectories, thereby failing to meet the stringent requirements of art therapy regarding dynamic emotional progression. To bridge this gap, the paper proposes EC-Script, a novel framework that introduces hierarchically guided large language model (LLM) agents into art therapy–oriented narrative generation for the first time. EC-Script achieves fine-grained alignment of emotional dynamics from global to local levels through a three-tier mechanism: emotional trajectory planning, character-driven scene generation, and emotion-controllable script writing. Experimental results demonstrate that the proposed method significantly outperforms current baselines in adherence to prescribed emotional trajectories, exhibiting superior controllability over narrative affect. This advancement offers a promising technical pathway for AI-assisted emotional healing.

Abstract

Art therapy plays a vital role in emotional healing, in which narrative creation acts as the primary vehicle for emotional expression. Given the inherently dynamic nature of emotions during healing, narratives with finely controlled emotional fluctuations enable individuals to safely project inner conflicts and achieve emotional catharsis. Recently, with the rapid development of Large Language Models (LLMs), automated narrative generation technology has provided a new pathway to support such artistic designs. However, while existing methods can produce fluent texts, they struggle to generate narratives that adhere to specified affective trajectories, failing to meet the demands of emotion-oriented psychological healing. To address these issues, this paper proposes EC-Script, an LLM agent-based framework that enables hierarchical control of the affective trajectory in narrative generation for emotional healing. To ensure that the generated narratives strictly follow the given emotional patterns, EC-Script establishes overall narrative direction through Emotion-Trajectory Planning, propels scene-level plot development with Character-Driven Scene Generation, and regulates local emotional changes of characters via Emotion-Controlled Script Writing. Ultimately, it outputs scene-by-scene script content that remains highly consistent with the preset affective trajectory. Experimental results demonstrate that EC-Script significantly outperforms baseline methods in affective trajectory adherence, exhibiting excellent and reliable emotional controllability, thereby providing effective technical support for AI-assisted emotional healing scenarios.

Problem

• art therapy
• emotional dynamics
• narrative generation
• affective trajectory
• emotional controllability

Innovation

• Emotion-Trajectory Control
• Hierarchical LLM Agents
• Controllable Narrative Generation
• Art Therapy
• Affective Consistency