Towards Human-Level Book-Writing Capability

• URL: http://arxiv.org/abs/2605.17064v1
• Date: Sat, 16 May 2026 16:10:41 GMT
• Title: Towards Human-Level Book-Writing Capability
• Abstract summary: We present a dataset construction and training framework for book-scale creative writing.<n>We derive a multi-resolution planning scaffold by summarizing each book at progressively finer levels.<n>We then invert this hierarchy during training: the model learns to expand a prompt into increasingly detailed plans and finally into the original human-authored book text.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models optimized for instruction following and agentic tasks remain poorly aligned with the requirements of high-quality creative writing. Fiction frequently depends on behaviors that assistant-tuned models are explicitly trained to avoid, particularly deception, moral ambiguity, and unreliable narration. As a result, generated stories often appear structurally correct while remaining stylistically generic, overly explanatory, or weakly grounded in human literary behavior. We present a dataset construction and training framework for book-scale creative writing that reframes supervised fine-tuning as a prompt-to-book generation task grounded in human-authored fiction. Starting from public-domain novels, we derive a multi-resolution planning scaffold by summarizing each book at progressively finer levels, from a high-level premise to chapter- and scene-level structure. We then invert this hierarchy during training: the model learns to expand a prompt into increasingly detailed plans and finally into the original human-authored book text. This formulation preserves human prose as the final supervised target while using intermediate summaries to make book-scale generation learnable. We train a long-context language model on these prompt-to-book trajectories and study whether this objective shifts generation away from assistant-style prose and toward human literary writing.

Related papers

• FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling [82.23236914620828]
  We formalize novel-to-film generation as dynamic cinematic world modeling, into two phases: construction and evolution.<n>We propose FilmWorld, an end-to-end agentic system where two groups of specialized agents collaborate to instantiate these phases.<n>Experiments demonstrate that FilmWorld consistently outperforms state-of-the-art video generation agent systems.
  arXiv  Detail & Related papers  (2026-07-21T12:28:58Z)
• Living the Novel: A System for Generating Self-Training Timeline-Aware Conversational Agents from Novels [50.43968216132018]
  We present an end-to-end system that transforms any literary work into an immersive, multi-character conversational experience.<n>This system is designed to solve two fundamental challenges for LLM-driven characters.
  arXiv  Detail & Related papers  (2025-12-08T11:57:46Z)
• 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)
• Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Style [48.08453439104245]
  We propose WriterAgent, a novel generation system designed to master the core aspects of literary pastiche.<n>WriterAgent is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence.<n>We evaluate WriterAgent on multilingual classics like Harry Potter and Dream of the Red Chamber, demonstrating its superiority over baselines.
  arXiv  Detail & Related papers  (2025-02-21T17:40:42Z)
• Agents' Room: Narrative Generation through Multi-step Collaboration [54.98886593802834]
  We propose a generation framework inspired by narrative theory that decomposes narrative writing into subtasks tackled by specialized agents.<n>We show that Agents' Room generates stories preferred by expert evaluators over those produced by baseline systems.
  arXiv  Detail & Related papers  (2024-10-03T15:44:42Z)
• Leveraging Natural Supervision for Language Representation Learning and Generation [8.083109555490475]
  We describe three lines of work that seek to improve the training and evaluation of neural models using naturally-occurring supervision. We first investigate self-supervised training losses to help enhance the performance of pretrained language models for various NLP tasks. We propose a framework that uses paraphrase pairs to disentangle semantics and syntax in sentence representations.
  arXiv  Detail & Related papers  (2022-07-21T17:26:03Z)
• Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence [59.51720326054546]
  We propose a long text generation model, which can represent the prefix sentences at sentence level and discourse level in the decoding process. Our model can generate more coherent texts than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2021-05-19T07:29:08Z)
• Content Planning for Neural Story Generation with Aristotelian Rescoring [39.07607377794395]
  Long-form narrative text manages a fluent impersonation of human writing, but only at the local sentence level, and lacks structure or global cohesion. We posit that many of the problems of story generation can be addressed via high-quality content planning, and present a system that focuses on how to learn good plot structures to guide story generation.
  arXiv  Detail & Related papers  (2020-09-21T13:41:32Z)

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.