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

Source: [BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation](<https://www.sota2.com/research/paper/69b8e0170636e5bf4afbead7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T05:00:11.244Z

Authors: Zhaoyi Li, Xu Zhang, Xiaojun Wan

Published: 2026-03-15T14:52:20.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Fiction Generation on 40 themes (test)](<https://www.sota2.com/research/sota/fiction-generation-on-40-themes-test.md>): Fiction Generation; 40 themes (test); NC: 62.5.

- [Narrative Generation Evaluation on Creativityprism 2025 (test)](<https://www.sota2.com/research/sota/narrative-generation-evaluation-on-creativityprism-2025-test.md>): Narrative Generation Evaluation; Creativityprism 2025 (test); Narrative Coherence (NC): 100.

- [Human Evaluation for Fiction Generation (test)](<https://www.sota2.com/research/sota/human-evaluation-for-fiction-generation-test.md>): Fiction Generation; Human Evaluation for Fiction Generation (test); Novelty (NC): 32.5.

- [Narrative Generation on Creativityprism (test)](<https://www.sota2.com/research/sota/narrative-generation-on-creativityprism-test.md>): Narrative Generation; Creativityprism (test); NC (%): 5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.14410>)

[PDF](<https://arxiv.org/pdf/2603.14410.pdf>)
