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

ConWriter is a training‑free framework that generates long‑form stories scene by scene, using static requirements, dynamic memory, symbolic state reasoning, and uncertainty‑aware risk signals to enforce consistency. It checks each new scene against required narrative transitions and repairs local errors before they propagate. Evaluations on ConStory‑Bench show that ConWriter matches or outperforms direct generation and a recent baseline, improving narrative consistency across multiple models and story lengths.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms