Understanding complex character relations is crucial for narrative analysis and efficient script evaluation, yet existing extraction methods often fail to handle long-form narratives with nuanced interactions. To address this challenge, we present CREFT, a novel sequential framework leveraging specialized Large Language Model (LLM) agents. First, CREFT builds a base character graph through knowledge distillation, then iteratively refines character composition, relation extraction, role identification, and group assignments. Experiments on a curated Korean drama dataset demonstrate that CREFT significantly outperforms single-agent LLM baselines in both accuracy and completeness. By systematically visualizing character networks, CREFT streamlines narrative comprehension and accelerates script review -- offering substantial benefits to the entertainment, publishing, and educational sectors.
@article{arxiv.2505.24553,
title = {CREFT: Sequential Multi-Agent LLM for Character Relation Extraction},
author = {Ye Eun Chun and Taeyoon Hwang and Seung-won Hwang and Byung-Hak Kim},
journal= {arXiv preprint arXiv:2505.24553},
year = {2025}
}