Saved in:
Bibliographic Details
Main Authors: Bang, Geonwoo, Kim, DongMyung, Oh, Hayoung
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2601.11529
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908772184621056
author Bang, Geonwoo
Kim, DongMyung
Oh, Hayoung
author_facet Bang, Geonwoo
Kim, DongMyung
Oh, Hayoung
contents Large Language Models (LLMs) hold great potential for web-based interactive applications, including browser games, online education, and digital storytelling platforms. However, LLM-based conversational agents suffer from spatiotemporal distortions when responding to variant user inputs, failing to maintain consistency with provided scenarios. We propose SNAP (Story and Narrative-based Agent with Planning), a framework that structures narratives into Cells with explicit Plans to prevent narrative drift in web environments. By confining context within each Cell and employing detailed plans that specify spatiotemporal settings, character actions, and plot developments, SNAP enables coherent and scenario-consistent dialogues while adapting to diverse user responses. Via automated and human evaluations, we validate SNAP's superiority in narrative controllability, demonstrating effective scenario consistency despite variant user inputs in web-based interactive storytelling.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11529
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation
Bang, Geonwoo
Kim, DongMyung
Oh, Hayoung
Human-Computer Interaction
Artificial Intelligence
Large Language Models (LLMs) hold great potential for web-based interactive applications, including browser games, online education, and digital storytelling platforms. However, LLM-based conversational agents suffer from spatiotemporal distortions when responding to variant user inputs, failing to maintain consistency with provided scenarios. We propose SNAP (Story and Narrative-based Agent with Planning), a framework that structures narratives into Cells with explicit Plans to prevent narrative drift in web environments. By confining context within each Cell and employing detailed plans that specify spatiotemporal settings, character actions, and plot developments, SNAP enables coherent and scenario-consistent dialogues while adapting to diverse user responses. Via automated and human evaluations, we validate SNAP's superiority in narrative controllability, demonstrating effective scenario consistency despite variant user inputs in web-based interactive storytelling.
title SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2601.11529