ReMemBench
Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks
Rutav Shah, Rajat Kumar Jenamani, Xiaohan Zhang, Lingfeng Sun, Roberto Martín-Martín, Yuke Zhu, et al. · 2026-06-15
- Modality
- Embodied & 3D
- Data
- Simulated
- Task · ground truth
- Act. · State+Act.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidencePartially evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- SMSpatial memoryPartially evaluated
- OSObject-state trackingDirectly evaluated
- TSTask-state trackingDirectly evaluated
Survey notes
Household tasks require within-episode recall because immediate sensory observations omit necessary information.