Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models

• URL: http://arxiv.org/abs/2605.29625v1
• Date: Thu, 28 May 2026 08:59:55 GMT
• Title: Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language Models
• Abstract summary: This paper explores a novel co-creation scenario involving children and Large Language Models (LLMs)<n>Our goal is to develop a multi-agent framework capable of producing high-quality narratives suitable for young players.
• Score: 1.3320917259299652
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The topic of Co-creation, i.e., AI agents interacting with humans to generate outputs (e.g., art), has gained significant attention recently. However, most studies focus on adult-human interactions in a digital setting. This paper explores a novel ludic co-creation scenario involving children and Large Language Models (LLMs) interacting through a physical board game to create written stories. Our goal is to develop a multi-agent framework capable of producing high-quality narratives suitable for young players. At the core of our approach is an iterative Writer-Editor process in which one LLM generates stories while another evaluates them and provides feedback for refinement. Through a simulation study involving multiple LLMs, we show that this iterative interaction consistently improves the perceived quality of generated stories across successive loops. The results indicate that a small number of refinement steps may be sufficient to achieve high-quality outputs in interactive storytelling systems.

Related papers

• OPEN-THEATRE: An Open-Source Toolkit for LLM-based Interactive Drama [62.00761178362677]
  Open-Theatre is the first open-source toolkit for experiencing and customizing LLM-based interactive drama.<n>It refines prior work with an efficient multi-agent architecture and a hierarchical retrieval-based memory system.
  arXiv  Detail & Related papers  (2025-09-20T14:53:14Z)
• MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio [48.820808691986805]
  MM-StoryAgent creates immersive narrated video storybooks with refined plots, role-consistent images, and multi-channel audio.<n>The framework enhances story attractiveness through a multi-stage writing pipeline.<n> MM-StoryAgent offers a flexible, open-source platform for further development.
  arXiv  Detail & Related papers  (2025-03-07T08:53:10Z)
• StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration [88.94832383850533]
  We propose a multi-agent framework designed for Customized Storytelling Video Generation (CSVG) StoryAgent decomposes CSVG into distinct subtasks assigned to specialized agents, mirroring the professional production process. Specifically, we introduce a customized Image-to-Video (I2V) method, LoRA-BE, to enhance intra-shot temporal consistency. Our contributions include the introduction of StoryAgent, a versatile framework for video generation tasks, and novel techniques for preserving protagonist consistency.
  arXiv  Detail & Related papers  (2024-11-07T18:00:33Z)
• 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)
• A Character-Centric Creative Story Generation via Imagination [15.345466372805516]
  We introduce a novel story generation framework called CCI (Character-centric Creative story generation via Imagination)<n> CCI features two modules for creative story generation: IG (Image-Guided Imagination) and MW (Multi-Writer model)<n>In the IG module, we utilize a text-to-image model to create visual representations of key story elements, such as characters, backgrounds, and main plots.<n>The MW module uses these story elements to generate multiple persona-description candidates and selects the best one to insert into the story, thereby enhancing the richness and depth of the narrative.
  arXiv  Detail & Related papers  (2024-09-25T06:54:29Z)
• SEED-Story: Multimodal Long Story Generation with Large Language Model [66.37077224696242]
  SEED-Story is a novel method that leverages a Multimodal Large Language Model (MLLM) to generate extended multimodal stories. We propose multimodal attention sink mechanism to enable the generation of stories with up to 25 sequences (only 10 for training) in a highly efficient autoregressive manner. We present a large-scale and high-resolution dataset named StoryStream for training our model and quantitatively evaluating the task of multimodal story generation in various aspects.
  arXiv  Detail & Related papers  (2024-07-11T17:21:03Z)
• From Words to Worlds: Transforming One-line Prompt into Immersive Multi-modal Digital Stories with Communicative LLM Agent [11.553884271082127]
  This paper introduces the StoryAgent framework to automate and refine digital storytelling. StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. Results demonstrate the framework's capability to produce coherent digital stories without reference videos.
  arXiv  Detail & Related papers  (2024-06-15T03:03:43Z)
• Collaborative Storytelling with Large-scale Neural Language Models [6.0794985566317425]
  We introduce the task of collaborative storytelling, where an artificial intelligence agent and a person collaborate to create a unique story by taking turns adding to it. We present a collaborative storytelling system which works with a human storyteller to create a story by generating new utterances based on the story so far.
  arXiv  Detail & Related papers  (2020-11-20T04:36:54Z)
• Cue Me In: Content-Inducing Approaches to Interactive Story Generation [74.09575609958743]
  We focus on the task of interactive story generation, where the user provides the model mid-level sentence abstractions. We present two content-inducing approaches to effectively incorporate this additional information. Experimental results from both automatic and human evaluations show that these methods produce more topically coherent and personalized stories.
  arXiv  Detail & Related papers  (2020-10-20T00:36:15Z)

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.