M3-Bench
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Lin Long, Yichen He, Wentao Ye, Yiyuan Pan, Yuan Lin, Hang Li, et al. · 2025-10-09
- Modality
- Video & streaming
- Data
- Real data
- Task · ground truth
- QA · Ans.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesPartially evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionNot evaluated
- TLTemporal localizationDirectly evaluated
- TRTemporal relationsDirectly evaluated
- MEMulti-event integrationDirectly evaluated
Survey notes
Videos simulate agent perceptual experience; future questions reference earlier events and test recall plus reasoning over long-term memory.