DISBench
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
Chenlong Deng, Mengjie Deng, Junjie Wu, Dun Zeng, Teng Wang, Qingsong Xie, et al. · 2026-05-29
- Modality
- Image
- Data
- Real data
- Task · ground truth
- Ret./Loc. · Ev.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidencePartially evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesNot evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionNot evaluated
- FGFine-grained visual detailPartially evaluated
- ETEntity trackingDirectly evaluated
- VCVisual state changePartially evaluated
Survey notes
Context-dependent image retrieval must connect clues across a user's chronological visual archive; individual image matching is insufficient.