evaluation-family · Source-linked discovery
Persistbench Beneficial Memory
Evaluates long-term memory risk in assistant behavior across three tasks: cross-domain memory leakage, memory-driven sycophancy, and beneficial memory usage.
OriginSidharth Pulipaka, Oliver Chen, Manas Sharma et al.TopicsGeneral capabilityStatusimported
Can support
Not independently assessed by FronteraEval yet.
Cannot support by itself
No inference beyond the upstream source should be made until the protocol is reviewed.