用计划驱动框架提升互动叙事一致性
SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation
- 将叙事拆解为带详细计划的单元，约束上下文范围
- 在多种用户输入下保持情节连贯性，减少叙事漂移
- 适合开发网页互动故事、教育应用等场景
大型语言模型在基于浏览器的互动应用（如网络游戏、在线教育、数字叙事平台）中具有巨大潜力。然而，基于LLM的对话代理在面对多变用户输入时，常出现时空错位，难以维持设定场景的一致性。本文提出SNAP（基于计划的故事与叙事代理），将叙事结构化为带有明确计划的“单元（Cells）”，通过限制每个单元内的上下文，并采用详尽的计划来规定时空背景、角色行为和剧情发展，实现与场景一致的连贯对话，同时适应多样化用户响应。通过自动化与人工评估，验证了SNAP在叙事可控性上的优势，在网页互动叙事中能有效保持场景一致性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。