BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation
This addresses the problem of generating structured and diverse narratives in Chinese fiction for AI applications, representing an incremental advance with a novel method for a known bottleneck.
The paper tackled the challenge of generating long-form linear fiction from open-ended themes by proposing BiT-MCTS, a theme-driven framework that improves narrative coherence, plot structure, and thematic depth, enabling substantially longer and more coherent stories as validated by experiments.
Generating long-form linear fiction from open-ended themes remains a major challenge for large language models, which frequently fail to guarantee global structure and narrative diversity when using premise-based or linear outlining approaches. We present BiT-MCTS, a theme-driven framework that operationalizes a "climax-first, bidirectional expansion" strategy motivated by Freytag's Pyramid. Given a theme, our method extracts a core dramatic conflict and generates an explicit climax, then employs a bidirectional Monte Carlo Tree Search (MCTS) to expand the plot backward (rising action, exposition) and forward (falling action, resolution) to produce a structured outline. A final generation stage realizes a complete narrative from the refined outline. We construct a Chinese theme corpus for evaluation and conduct extensive experiments across three contemporary LLM backbones. Results show that BiT-MCTS improves narrative coherence, plot structure, and thematic depth relative to strong baselines, while enabling substantially longer, more coherent stories according to automatic metrics and human judgments.