Benchmark RadareMEM-Bench
eMEM-Bench v1 evaluates embodied memory systems through 988 probes across eight cognitive-psychology paradigms (DRM lures, pattern separation, pattern completion, source monitoring, context-dependent retrieval, long-horizon interference, serial position, foil retention curve) in ProcTHOR-10K scenes.
- Released
- 2026-06-02
- Readiness
- Paper only
- Primary field
- Robotics & Autonomous Systems
Why it matters
Existing agent memory benchmarks lack diagnostic depth. eMEM-Bench provides interpretable results tied to memory-systems literature, allowing fine-grained comparison of embodied memory architectures beyond surface-task accuracy.
Motivation
We present eMEM (Embodied Memory), a hybrid graph-based memory system for embodied agents operating in physical environments.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.