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

arXiv: https://arxiv.org/abs/2608.05169 · HTML: https://mlsanity.com/paper/2608.05169/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 10 of 10)

- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs](https://mlsanity.com/paper/2504.15965/) (2025)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [StoryWriter: A Multi-Agent Framework for Long Story Generation](https://mlsanity.com/paper/2506.16445/) (2025)
- [A Cognitive Writing Perspective for Constrained Long-Form Text Generation](https://mlsanity.com/paper/2502.12568/) (2025)
- [LongStory: Coherent, Complete and Length Controlled Long story Generation](https://mlsanity.com/paper/2311.15208/) (2023)
- [Lost in Stories: Consistency Bugs in Long Story Generation by LLMs](https://mlsanity.com/paper/2603.05890/) (2026)
- [HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents](https://mlsanity.com/paper/2604.16839/) (2026)

## Abstract (arXiv)

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-form 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 across four long-story tasks, three target lengths, and multiple base LLMs following the official evaluation protocol. Across models and story lengths, ConWriter consistently matches or improves upon direct generation and outperforms the recent training-free baseline DOME in narrative consistency. These results demonstrate the effectiveness of lightweight neuro-symbolic consistency control for training-free long-form story generation. Code is available on hrefhttps://github.com/jindongli-Ai/ConWriterGitHub.