MUSE:一种通过闭环认知协调的多智能体框架用于无约束故事构思
MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration
AI总结:
MUSE通过闭环认知协调的多智能体框架,提升长篇叙事的连贯性与多模态一致性。
摘要:
从简短的用户提示生成长篇音频-视觉故事仍然具有挑战性,因为存在意图执行的差距,其中高层次的叙事意图必须在连贯的、按镜头级的多模态生成过程中保持一致。现有方法通常依赖于前馈管道或仅提示的细化,这往往导致随着序列变长而出现语义漂移和身份不一致。我们通过将讲故事制定为闭环约束执行问题来解决这一挑战,并提出MUSE,一种多智能体框架,通过迭代的计划-执行-验证-修订循环协调生成。MUSE将叙事意图转化为显式的、机器可执行的控制,以控制身份、空间组成和时间连续性,并应用针对性的多模态反馈来在生成过程中纠正违规行为。为了评估无参考的开放性叙事,我们引入了MUSEBench,一种无参考评估协议,通过人类判断验证。实验表明,与代表性基线相比,MUSE在长时间跨度的叙事连贯性、跨模态身份一致性和电影质量方面显著改进。
英文摘要:
Generating long-form audio-visual stories from a short user prompt remains challenging due to an intent-execution gap, where high-level narrative intent must be preserved across coherent, shot-level multimodal generation over long horizons. Existing approaches typically rely on feed-forward pipelines or prompt-only refinement, which often leads to semantic drift and identity inconsistency as sequences grow longer. We address this challenge by formulating storytelling as a closed-loop constraint enforcement problem and propose MUSE, a multi-agent framework that coordinates generation through an iterative plan-execute-verify-revise loop. MUSE translates narrative intent into explicit, machine-executable controls over identity, spatial composition, and temporal continuity, and applies targeted multimodal feedback to correct violations during generation. To evaluate open-ended storytelling without ground-truth references, we introduce MUSEBench, a reference-free evaluation protocol validated by human judgments. Experiments demonstrate that MUSE substantially improves long-horizon narrative coherence, cross-modal identity consistency, and cinematic quality compared with representative baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。