SMMBench
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
Huacan Chai, Yukai Wang, Yingxuan Yang, Dan Peng, Yuanyi Song, Zhihui Fu, et al. · 2026-05-15
- Modality
- Image
- Data
- Hybrid (real + synthetic/simulated)
- Task · ground truth
- QA/Act. · Ans.+Ev.+Prov.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesDirectly evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- FGFine-grained visual detailPartially evaluated
- ETEntity trackingDirectly evaluated
- VCVisual state changePartially evaluated
Survey notes
Sources are ingested in temporal order before the query; retrieval is tested against distributed multimodal evidence, including conflicting records and function-call decisions.