RoboMemArena
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
Huashuo Lei, Wenxuan Song, Huarui Zhang, Jieyuan Pei, Jiayi Chen, Haodong Yan, et al. · 2026-05-11
- Modality
- Embodied & 3D
- Data
- Hybrid (real + synthetic/simulated)
- Task · ground truth
- Act./Learn · State+Act.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- SMSpatial memoryDirectly evaluated
- OSObject-state trackingDirectly evaluated
- TSTask-state trackingDirectly evaluated
Survey notes
Historically necessary subtasks are constructed so the current observation cannot supply all information needed for action.