Benchmark
MEMOBench
What is MEMOBench?
Evaluates robotic manipulation policies on memory fidelity via 30 history-dependent tasks with annotated checkpoints measuring storage, update, and compression…
- Released
- 2026-09-07
- Evaluates
- Robot manipulation, Robotics, Robotics & Embodied AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2609.07047
MEMOBench paper and code
No reported scores are on record for this benchmark yet.