Metraipolis › archive › dc_25faf6aa0ede
ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control — arXiv:2608.05169
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05169
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:27:04.403Z
- SHA-256 of the archived text
c427933e423dfb4520ff9550455c1c8a4d9b1163b789ab3db9a49bbd5686883b- Stable URL of this page
https://metraipolis.com/documento/dc_25faf6aa0ede
How to cite
ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control — arXiv:2608.05169 — arXiv (en), https://arxiv.org/abs/2608.05169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25faf6aa0ede (Metraipolis archive dc_25faf6aa0ede, sha256 c427933e423dfb4520ff9550455c1c8a4d9b1163b789ab3db9a49bbd5686883b)
BibTeX
@misc{dc25faf6aa0ede,
title = {ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control — arXiv:2608.05169},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05169},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25faf6aa0ede; sha256 c427933e423dfb4520ff9550455c1c8a4d9b1163b789ab3db9a49bbd5686883b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 \href{ this https URL }{GitHub}.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.05169 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-25T21:24:38.178Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).