EvoState: Closed-Loop Visual State Management for Long-Form Video Generation

arXiv:2606.16184v2 Announce Type: replace Abstract: Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. Existing methods encode past shots as compressed context, implicit features, or retrieved frames, making it hard to tell whether new visual evidence is another view of an existing appearance, an evolved state of the same identity, or a newly introduced entity. We propose EvoState, an agentic framework that formulates multi-shot generation as entity-centric evolving visual state management, following a state-observation-update-propagation cycle. An entity-centric Visual State Memory separates persistent identity anchors from their evolved states and observations, so each shot retrieves the required state, accumulates complementary views, and reactivates earlier appearances without conflating them. A Visual State Analyzer reconciles the text-visual-memory triplet by observing generated visual evidence, updating generation conditions according to realized outcomes and memory states, and propagating inferred state transitions into memory and future prompts. As a result, generation is conditioned on an evolving state history grounded in what has been realized, rather than solely on planned textual descriptions. Experiments on our curated StoryBench benchmark demonstrate substantial improvements in identity preservation, state-transition correctness, and narrative coherence over state-of-the-art methods.

Source: arXiv cs.CV | 2026-10-06

Related