VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding

Excerpt

arXiv:2610.06672v1 Announce Type: cross Abstract: Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended temporal spans. Existing approaches broadly follow two paradigms: query-driven exploration, which is sensitive to localization errors, and query-independent memory construction, which may omit question-specific details. We introduce VideoTapestry, a training-free multi-agent framework that adapts