Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.03028 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910009928974336 |
|---|---|
| author | Sun, Wenzhang Wang, Zhenyu Hu, Zhangchi Wang, Chunfeng Li, Hao Chen, Wei |
| author_facet | Sun, Wenzhang Wang, Zhenyu Hu, Zhangchi Wang, Chunfeng Li, Hao Chen, Wei |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03028 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration Sun, Wenzhang Wang, Zhenyu Hu, Zhangchi Wang, Chunfeng Li, Hao Chen, Wei Computer Vision and Pattern Recognition 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. |
| title | MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.03028 |