04:00
2026-06-29
arxiv.org
artificial-intelligence
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Researchers introduced DMV-Bench, the first interactive benchmark for multimodal-agent visual memory, testing agents' ability to recall visual cues from product images in a simulated e-commerce enviroβ¦