GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing

TL;DR

GLANCE is a multi-agent framework that improves music-grounded nonlinear video editing by integrating global planning and local refinement, outperforming existing methods on a new benchmark.

Contribution

The paper introduces GLANCE, a novel global-local coordination multi-agent system with a bi-loop architecture and a new benchmark for music-grounded video editing.

Findings

GLANCE outperforms prior baselines by 33.2% and 15.6% on two tasks.

The framework effectively manages cross-segment conflicts and long-range constraints.

Human evaluation confirms the high quality of generated videos.

Abstract

Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos while aligning with music rhythm, user intent, story completeness, and long-range structural constraints. Existing approaches typically rely on fixed pipelines or simplified retrieval-and-concatenation paradigms, limiting their ability to adapt to diverse prompts and heterogeneous source materials. In this paper, we present GLANCE, a global-local coordination multi-agent framework for music-grounded nonlinear video editing. GLANCE adopts a bi-loop architecture for better editing practice: an outer loop performs long-horizon planning and task-graph construction, and an inner loop adopts the "Observe-Think-Act-Verify" flow for segment-wise editing tasks and their refinements. To address the cross-segment and global conflict emerging after subtimelines composition, we introduce a dedicated global-local coordination mechanism with both preventive and corrective components, which includes a novelly designed context controller, conflict region decomposition module, and a bottom-up dynamic negotiation mechanism. To support rigorous evaluation, we construct MVEBench, a new benchmark that factorizes editing difficulty along task type, prompt specificity, and music length, and propose an agent-as-a-judge evaluation framework for scalable multi-dimensional assessment. Experimental results show that GLANCE consistently outperforms prior research baselines and open-source product baselines under the same backbone models. With GPT-4o-mini as the backbone, GLANCE improves over the strongest baseline by 33.2% and 15.6% on two task settings, respectively. Human evaluation further confirms the quality of the generated videos and validates the effectiveness of the proposed evaluation framework.