SOURCE-LINKED INTELLIGENCE

BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Multimodal agents can create complex videos in software such as Blender by coding without relying on diffusion models. Yet video understanding benchmarks still evaluate models mainly through question answering. If an agent truly understands a video, it can reconstruct it programmatically. We introduce BVB, Blender-VideoBench, a benchmark that tests this ability by asking agents to reconstruct real-world videos as animated Blender scenes. To ensure fair comparison, each agent programs the reconstruction through a lightweight harness, Mini-BVB, in an identical sandbox under a shared cost limit.

Read original source ↗ Open in workspace

recordType

paper

region

Global