From Meeting at 14 May 2025, here is the literature review about Benchmark on dialogues that focus on Long-Term Memory.

Link to the full survey reading note: Reading - (Survey) Rethinking Memory in AI

BenchmarkDomainSessQContext DepthCore Memory Abilities
IEMRKUTRABS
MSC (Xu et al., 2022a)Open-Domain5k-1k
DuLeMon (Xu et al., 2022b)Open-Domain30k-1k
MemoryBank (Zhong et al., 2024)Personal3001945k
PerLTQA (Du et al., 2024)Personal4k85931M∗
LoCoMo (Maharana et al., 2024)Personal1k751210k
DialSim (Kim et al., 2024)TV Shows1k–2k1M350k✓∗∗
LongMemEval (this work)Personal50k500115k, 1.5M