Metraipolis › archive › dc_2576ff8515be

When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations — arXiv:2608.15654

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15654
License (as archived)
CC0-1.0
Archived
2026-10-18T18:04:09.400Z
SHA-256 of the archived text
449622098c98a3ce3e08521786fce02897dd0cb21ac9fcc6d9a4139b9ec03fbf
Stable URL of this page
https://metraipolis.com/documento/dc_2576ff8515be

How to cite

When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations — arXiv:2608.15654 — arXiv (en), https://arxiv.org/abs/2608.15654 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2576ff8515be (Metraipolis archive dc_2576ff8515be, sha256 449622098c98a3ce3e08521786fce02897dd0cb21ac9fcc6d9a4139b9ec03fbf)
BibTeX
@misc{dc2576ff8515be,
  title = {When Stories Evolve: Benchmarking LLM Storytelling Across Agent Architectures in Open-Ended World Simulations — arXiv:2608.15654},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15654},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2576ff8515be; sha256 449622098c98a3ce3e08521786fce02897dd0cb21ac9fcc6d9a4139b9ec03fbf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15654. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models can write fluent stories, but open-ended storytelling requires more than local fluency. In evolving world simulations and AI-native games, models must preserve facts, relationships, causal dependencies, and character states as the world changes. We introduce WSE-bench, a process benchmark that separately evaluates sustained generation, canonical coherence, and meaningful development in dynamic LLM storytelling. Generation Coverage records the proportion of planned narrative steps produced; Consistency tracks when canon breaks; and Richness measures how meaningfully branching, player-shaped trajectories develop. Across frontier models, Consistency and Richness do not form a smooth trade-off: their empirical Pareto frontier is non-concave, with several non-dominated intermediate configurations that no positive linear weighting can select. Added structure can enrich trajectories, but it does not uniformly improve coherence and may shorten them. Model scale chiefly improves sustained generation, without producing reliable gains in canonical coherence or meaningful development. These results show that sustained generation, canonical coherence, and meaningful development are distinct and sometimes competing capacities. WSE-bench makes those dynamics visible by extending narrative evaluation from finished stories to the processes that create them.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15654 — 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 2026-10-18T16:29:14.038Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).