Metraipolis › archive › dc_6fde68dfbe4d

Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs — arXiv:2611.01954

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01954
License (as archived)
CC0-1.0
Archived
2026-11-03T18:23:25.826Z
SHA-256 of the archived text
2fa1431c37943994604fcb5b475e4a1173ee80ccd4267989ef7039eb5d909c58
Stable URL of this page
https://metraipolis.com/documento/dc_6fde68dfbe4d

How to cite

Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs — arXiv:2611.01954 — arXiv (en), https://arxiv.org/abs/2611.01954 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6fde68dfbe4d (Metraipolis archive dc_6fde68dfbe4d, sha256 2fa1431c37943994604fcb5b475e4a1173ee80ccd4267989ef7039eb5d909c58)
BibTeX
@misc{dc6fde68dfbe4d,
  title = {Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs — arXiv:2611.01954},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01954},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6fde68dfbe4d; sha256 2fa1431c37943994604fcb5b475e4a1173ee80ccd4267989ef7039eb5d909c58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01954. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traditional interactive narrative systems offer strong authorial control and structural coherence but often restrict player agency. In contrast, LLM-driven narratives enable open-ended generation and greater flexibility, yet frequently suffer from inconsistency and diminished narrative control. To navigate this trade-off, we propose a hybrid narrative framework that dynamically balances pre-authored content with real-time LLM generation via semantic similarity alignment. Additionally, sustaining narrative quality over extended gameplay remains a core challenge in LLM-based storytelling. To address this, we introduce a self-evolving, feedback-driven optimization framework that leverages in-context learning to iteratively refine prompts, eliminating the need for manual prompt engineering. Through a case study and participant-based evaluation, we show that our framework enhances narrative coherence while preserving player agency, effectively aligning generated content with both authorial intent and evolving player behavior.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.01954 — 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 2026-11-03T18:10:07.945Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).