BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation

arXiv:2603.14410v3 Announce Type: replace Abstract: 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.

Related

• Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories
• DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
• Latent-Condensed Transformer for Efficient Long Context Modeling
• E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning

Source: arXiv cs.CL | 2026-04-14