MEMEVO: A Memory-Evolved Video Agent for Long Video Understanding

Agent-based frameworks grounded in vision-language models (VLMs) have emerged as a dominant paradigm for long video understanding. Yet, prevailing agents lack the core capacity for dynamic memory evolution, failing to transform ephemeral perceptions into a continuously growing, adaptive knowledge system and thus inducing inefficient redundant exploration during reasoning. To this end, we present MEMEVO, an online Memory-Evolved Video Agent framework centered on dynamic memory evolution that leverages accumulating multi-turn queries to actively drive progressive memory evolution, establishing a long-lived memory system for knowledge accumulation. Central to MEMEVO is a four-level Hierarchical Self-Evolved Memory, which constructs memory bottom-up via progressive abstraction, distilling transient perceptions into reusable, query-agnostic event nodes organized within a temporal-semantic graph, while realizing active memory evolution through event insertion, duplicate merging, and redundant pruning. To mitigate redundant retrieval in the evolved memory, we devise a State-Conditioned Graph Memory Retrieval mechanism that guides efficient navigation of the memory space, integrating State-Conditioned Graph Routing and Meta-Cognitive Stopping criteria to ensure sufficient evidence acquisition without re-exploration. Extensive benchmarking confirms that MEMEVO achieves state-of-the-art performance on reasoning-intensive tasks (\textcolor[HTML]00FF00+6.1% VideoMMMU, \textcolor[HTML]00FF00+4.8% LongVideoBench), while facilitating cross-query knowledge reuse and cross-model generalization.