MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing

• URL: http://arxiv.org/abs/2609.15188v2
• Date: Tue, 15 Sep 2026 10:42:46 GMT
• Title: MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing
• Abstract summary: We formulate Vibe Narrativizing as the task of turning natural-language writing requirements into a finished story.<n>We present MUSE, a Theory-Harnessed Story Engine.<n>MUSE derives reusable guidance from Robert McKee's story theory through rule atomization, semantic consolidation, and mechanism abstraction.
• Score: 14.61147082072489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs can generate fluent prose. Turning this capability into high-quality stories requires coordinating decisions about plot, character, and language across planning, drafting, and revision. Guiding these decisions presents two bottlenecks: the quality of story guidance and its sustained use. We formulate Vibe Narrativizing as the task of turning natural-language writing requirements into a finished story and present MUSE, a Theory-Harnessed Story Engine. MUSE derives reusable guidance from Robert McKee's story theory through rule atomization, semantic consolidation, and mechanism abstraction. A single source of truth and layered disclosure organize this guidance, while examples clarify principles that depend on context and aesthetic judgment. An agent harness preserves creative 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 traces a requested object from its thematic role to climactic actions. Across four base models, MUSE improves WritingBench by 1.6--4.8 points over zero-shot generation and raises LongStoryEval by more than ten points on three. ConStory-Bench consistency error density remains in the low single digits for all four models, below every reproduced story-system baseline on three. Ablations locate the largest quality contribution in structural design, voice-specific effects in the character path, and further gains in revision.

Related papers

• Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents [5.808135444478086]
  We propose REVERIEMEM, a three-layer memory architecture for book-based character agents.<n>The episodic layer stores first-person scene memories; the semantic layer stores visibility-tagged facts; and the personality layer stores situation-dependent speech and behaviour patterns.<n>For evaluation, we construct KBF-QA, a 4,386-question benchmark over eight novels for testing knowledge boundaries.
  arXiv  Detail & Related papers  (2026-06-24T09:37:49Z)
• Controllable Narrative Rendering for Enhanced Assisted Writing [12.310927788766852]
  We propose Loom, an assisted writing framework grounded in the narratological distinction between story and discourse.<n>Lo Loom achieves the highest overall quality score, yielding substantial gains in factual integrity and descriptive intensity.
  arXiv  Detail & Related papers  (2026-05-05T00:35:45Z)
• S^2tory: Story Spine Distillation for Movie Script Summarization [12.310927788766854]
  Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure.<n>We introduce S2tory, a framework that leverages character development trajectories to identify plot nuclei.<n>Experiments on the MovieSum dataset demonstrate state-of-the-art semantic fidelity at approximately 3.5x compression, and zero-shot evaluation on BookSum confirms strong out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-05-05T00:25:09Z)
• Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books [52.08691427871138]
  We propose a training framework that decouples reasoning from generation.<n>Our approach consists of a reasoning model that produces a structured QA reasoning trace and a generation model that conditions on this trace to produce the final character description.
  arXiv  Detail & Related papers  (2026-04-13T13:19:56Z)
• STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generation [17.553025200797986]
  We introduce Storyteller, a novel approach that systemically improves the coherence and consistency of automatically generated stories.<n>In experiments, Storyteller significantly outperforms existing approaches, achieving an 84.33% average win rate.<n>At the same time, it is also far ahead in other aspects including creativity, coherence, engagement, and relevance.
  arXiv  Detail & Related papers  (2025-06-03T00:54:00Z)
• STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives [82.19488717416351]
  This paper introduces StoryAnchors, a unified framework for generating high-quality, multi-scene story frames.<n>StoryAnchors employs a bidirectional story generator that integrates both past and future contexts to ensure temporal consistency.<n>It also integrates Multi-Event Story Frame Labeling and Progressive Story Frame Training, enabling the model to capture both overarching narrative flow and event-level dynamics.
  arXiv  Detail & Related papers  (2025-05-13T08:48:10Z)
• Learning to Reason for Long-Form Story Generation [84.09733333295338]
  We propose a general story-generation task (Next-Chapter Prediction) and a reward formulation (Verified Rewards via Completion Likelihood Improvement)<n>We learn to reason over a story's condensed information and generate a detailed plan for the next chapter.<n>Our reasoning is evaluated via the chapters it helps a story-generator create, and compared against non-trained and supervised finetuning (SFT) baselines.
  arXiv  Detail & Related papers  (2025-03-28T18:48:26Z)
• Generating Visual Stories with Grounded and Coreferent Characters [63.07511918366848]
  We present the first model capable of predicting visual stories with consistently grounded and coreferent character mentions.<n>Our model is finetuned on a new dataset which we build on top of the widely used VIST benchmark.<n>We also propose new evaluation metrics to measure the richness of characters and coreference in stories.
  arXiv  Detail & Related papers  (2024-09-20T14:56:33Z)
• Are Large Language Models Capable of Generating Human-Level Narratives? [114.34140090869175]
  This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects. We show that explicit integration of discourse features can enhance storytelling, as is demonstrated by over 40% improvement in neural storytelling.
  arXiv  Detail & Related papers  (2024-07-18T08:02:49Z)
• MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation [50.01780173691132]
  We introduce Modular Story Premise Synthesis (MoPS) MoPS breaks down story premises into modules like background and persona for automated design and generation. Thorough evaluations demonstrate that our synthesized premises excel in diversity, fascination, completeness, and originality.
  arXiv  Detail & Related papers  (2024-06-09T08:31:14Z)
• StoryVerse: Towards Co-authoring Dynamic Plot with LLM-based Character Simulation via Narrative Planning [8.851718319632973]
  Large Language Models (LLMs) drive the behavior of virtual characters, allowing plots to emerge from interactions between characters and their environments. We propose a novel plot creation workflow that mediates between a writer's authorial intent and the emergent behaviors from LLM-driven character simulation. The process creates "living stories" that dynamically adapt to various game world states, resulting in narratives co-created by the author, character simulation, and player.
  arXiv  Detail & Related papers  (2024-05-17T23:04:51Z)
• CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions [10.694612203803146]
  This paper proposes a model for fine-grained control on the story. It allows the generation of customized stories with characters, corresponding actions and emotions arbitrarily assigned. It has strong controllability to generate stories according to the fine-grained personalized guidance.
  arXiv  Detail & Related papers  (2022-10-11T07:37:50Z)
• PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking [128.76063992147016]
  We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative.
  arXiv  Detail & Related papers  (2020-04-30T17:16:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.