Metraipolis › archive › dc_f7daa7cf0668

MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing — arXiv:2609.15188

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15188
License (as archived)
CC0-1.0
Archived
2026-10-15T23:15:56.941Z
SHA-256 of the archived text
ff5fb6254207b0c3d963d264084c86c6ab76b487ca29c1beea9c8c8a368d6ada
Stable URL of this page
https://metraipolis.com/documento/dc_f7daa7cf0668

How to cite

MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing — arXiv:2609.15188 — arXiv (en), https://arxiv.org/abs/2609.15188 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f7daa7cf0668 (Metraipolis archive dc_f7daa7cf0668, sha256 ff5fb6254207b0c3d963d264084c86c6ab76b487ca29c1beea9c8c8a368d6ada)
BibTeX
@misc{dcf7daa7cf0668,
  title = {MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing — arXiv:2609.15188},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15188},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f7daa7cf0668; sha256 ff5fb6254207b0c3d963d264084c86c6ab76b487ca29c1beea9c8c8a368d6ada},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15188. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs have been able to generate fluent prose, but high-quality stories also require coordinated decisions about plot, character, and language across planning, drafting, and revision. We formulate Vibe Narrativizing as turning natural-language writing requirements into a finished story. MUSE, a Theory-Harnessed Story Engine, addresses two bottlenecks: rule quality and sustained rule realization. Story theory supplies the rules, and a practical agent harness puts them to work. Knowledge engineering organizes Robert McKee's theory through rule atomization, semantic consolidation, mechanism abstraction, a single source of truth, and layered disclosure; typical examples clarify judgments that depend on context and aesthetic purpose. The harness preserves story decisions in intermediate deliverables across design, character performance, scene composition, and revision. Context engineering supplies each role with relevant guidance and decisions; a masterwork corpus provides inspiration and prose references. A worked example follows a requested object from its thematic role to climactic actions. Across four base models, MUSE improves WritingBench by 1.1 to 6.2 points over zero-shot generation; it is the only multi-stage system in our comparison to do so. It also raises LongStoryEval by more than ten points on three of the four models. ConStory-Bench consistency error density remains in the low single digits for all four models, below every reproduced story-system baseline on three of the four models. Ablations locate the largest quality contribution in structural design, voice-specific effects in the character path, and further gains in revision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.15188 — 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 2026-10-15T22:51:09.936Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).