# StoryWriter: A Multi-Agent Framework for Long Story Generation

arXiv: https://arxiv.org/abs/2506.16445 · HTML: https://mlsanity.com/paper/2506.16445/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 17 of 17)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [Agents' Room: Narrative Generation through Multi-step Collaboration](https://mlsanity.com/paper/2410.02603/) (2024)
- [Do Language Models Enjoy Their Own Stories? Prompting Large Language Models for Automatic Story Evaluation](https://mlsanity.com/paper/2405.13769/) (2024)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [LongGenBench: Long-context Generation Benchmark](https://mlsanity.com/paper/2410.04199/) (2024)
- [Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2212.04634/) (2022)
- [Creating Suspenseful Stories: Iterative Planning with Large Language Models](https://mlsanity.com/paper/2402.17119/) (2024)
- [Improving Pacing in Long-Form Story Planning](https://mlsanity.com/paper/2311.04459/) (2023)
- [MoPS: Modular Story Premise Synthesis for Open-Ended Automatic Story Generation](https://mlsanity.com/paper/2406.05690/) (2024)

## Built on by (most cited first, 19 of 19)

- [RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction](https://mlsanity.com/paper/2601.06966/) (2026)
- [FinDebate: Multi-Agent Collaborative Intelligence for Financial Analysis](https://mlsanity.com/paper/2509.17395/) (2025)
- [AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents](https://mlsanity.com/paper/2603.26034/) (2026)
- [Who Wrote the Book? Detecting and Attributing LLM Ghostwriters](https://mlsanity.com/paper/2603.28054/) (2026)
- [Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents](https://mlsanity.com/paper/2606.25632/) (2026)
- [From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives](https://mlsanity.com/paper/2607.00918/) (2026)
- [Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives](https://mlsanity.com/paper/2608.08160/) (2026)
- [StoryAlign: Evaluating and Training Reward Models for Story Generation](https://mlsanity.com/paper/2605.04831/) (2026)
- [StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment](https://mlsanity.com/paper/2605.28073/) (2026)
- [CreAgentive: An Agent Workflow Driven Multi-Category Creative Generation Engine](https://mlsanity.com/paper/2509.26461/) (2025)
- [LitVISTA: A Benchmark for Narrative Orchestration in Literary Text](https://mlsanity.com/paper/2601.06445/) (2026)
- [BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation](https://mlsanity.com/paper/2603.14410/) (2026)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution](https://mlsanity.com/paper/2604.12776/) (2026)
- [BOOKMARKS: Efficient Active Storyline Memory for Role-playing](https://mlsanity.com/paper/2605.14169/) (2026)
- [ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control](https://mlsanity.com/paper/2608.05169/) (2026)
- [StorySpark: Module-wise Evolutionary Search for Story Premise Generation](https://mlsanity.com/paper/2608.12336/) (2026)
- [SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation](https://mlsanity.com/paper/2609.05938/) (2026)
- [Scaling Long-Form Story Generation via Narrative State Tracking](https://mlsanity.com/paper/2609.35759/) (2026)

## Abstract (arXiv)

Long story generation remains a challenge for existing large language models (LLMs), primarily due to two main factors: (1) discourse coherence, which requires plot consistency, logical coherence, and completeness in the long-form generation, and (2) narrative complexity, which requires an interwoven and engaging narrative. To address these challenges, we propose StoryWriter, a multi-agent story generation framework, which consists of three main modules: (1) outline agent, which generates event-based outlines containing rich event plots, character, and event-event relationships. (2) planning agent, which further details events and plans which events should be written in each chapter to maintain an interwoven and engaging story. (3) writing agent, which dynamically compresses the story history based on the current event to generate and reflect new plots, ensuring the coherence of the generated story. We conduct both human and automated evaluation, and StoryWriter significantly outperforms existing story generation baselines in both story quality and length. Furthermore, we use StoryWriter to generate a dataset, which contains about 6,000 high-quality long stories, with an average length of 8,000 words. We train the model Llama3.1-8B and GLM4-9B using supervised fine-tuning on LongStory and develop StoryWriterGLM and StoryWriterGLM, which demonstrates advanced performance in long story generation.