ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control

# ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control
Source: [https://arxiv.org/abs/2608.05169](https://arxiv.org/abs/2608.05169)
[View PDF](https://arxiv.org/pdf/2608.05169)

> Abstract:Long\-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting\-based methods often accumulate temporal, factual, character, commonsense, and stylistic errors as the story grows\. We propose ConWriter, a training\-free framework for consistency\-aware long story generation\. ConWriter writes stories incrementally at the scene level, guided by static story requirements, dynamic narrative memory, symbolic state reasoning, and uncertainty\-aware risk signals\. Rather than treating long\-story generation as a single free\-form decoding process, ConWriter maintains evolving story states, checks whether new scenes satisfy required narrative transitions, and uses uncertainty\-aware risk signals to prioritize validation and localized repair\. This enables consistency control during generation, before local errors propagate into later scenes\. We evaluate ConWriter on ConStory\-Bench, covering four long\-story tasks: continuation, generation, expansion, and completion\. Due to the high cost of long\-form generation and evaluation, we use the first five cases from each task and test 3k, 6k, and 12k target lengths across Qwen3\.5\-Plus, DeepSeek\-V4\-Flash, and GPT\-5 series\. Experiments follow the official ConStory\-Bench evaluation protocol\.

## Submission history

From: Jindong Li \[[view email](https://arxiv.org/show-email/8e1baefc/2608.05169)\] **\[v1\]**Wed, 27 May 2026 17:53:18 UTC \(3,295 KB\)