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

arXiv: https://arxiv.org/abs/2603.14410 · HTML: https://mlsanity.com/paper/2603.14410/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 11 of 11)

- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Story Realization: Expanding Plot Events into Sentences](https://mlsanity.com/paper/1909.03480/) (2019)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation](https://mlsanity.com/paper/2506.10540/) (2025)
- [StoryWriter: A Multi-Agent Framework for Long Story Generation](https://mlsanity.com/paper/2506.16445/) (2025)
- [A Character-Centric Creative Story Generation via Imagination](https://mlsanity.com/paper/2409.16667/) (2024)
- [MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions](https://mlsanity.com/paper/2412.02897/) (2024)
- [COS(M+O)S: Curiosity and RL-Enhanced MCTS for Exploring Story Space via Language Models](https://mlsanity.com/paper/2501.17104/) (2025)
- [Quantification of Biodiversity from Historical Survey Text with LLM-based Best-Worst Scaling](https://mlsanity.com/paper/2502.04022/) (2025)

## Abstract (arXiv)

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.