MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery
MEMPROBE is the first benchmark to study memory recovery directly, reconstructing the user state a system retains and scoring it against ground truth, and is seen as a step toward an environment where agents are trained to remember their users, growing more faithful the longer they know them.
En-Ze Ma, Yufan Zhou, Wei-Chieh Huang et al.
· 4 citations