MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration

TL;DR

MUSE is a multi-agent framework that enhances long-form audio-visual storytelling by maintaining coherence and identity through a closed-loop control system, validated by a new reference-free evaluation protocol.

Contribution

It introduces a novel multi-agent, closed-loop approach for unconstrained story envisioning, addressing semantic drift and identity inconsistency in long narratives.

Findings

Significantly improves narrative coherence over long horizons

Enhances cross-modal identity consistency

Produces higher cinematic quality compared to baselines

Abstract

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.